AI Core

997 items

Microsoft Research Sep 29, 2026
Microsoft Research introduces Quine, a research system combining a world model of biology trained jointly across modalities including sequence, structure, function, cellular state, and imaging with a harness connecting scientific tools, literature, the wet lab, and researchers; with the Broad Institute it used the system in pancreatic ductal adenocarcinoma (PDAC) to predict and prioritize thousands of compounds by their potential to shift tumor cells between therapeutically relevant states, wet-lab assays showed Quine's highest-ranked compounds produced the largest intended shifts, the whole process from narrowing the search space to prioritizing a handful of candidates took just one weekend, and the experiments also bore out the model's prediction of a distinct third phenotype.
Microsoft Research introduces Quine, a research system combining a world model of biology trained jointly across modalities including sequence, structure, function, cellular state, and imaging with a harness connecting scientific tools, literature, the wet lab, and researchers; with the Broad Institute it used the system in pancreatic ductal adenocarcinoma (PDAC) to predict and prioritize thousands of compounds by their potential to shift tumor cells between therapeutically relevant states, wet-lab assays showed Quine's highest-ranked compounds produced the largest intended shifts, the whole process from narrowing the search space to prioritizing a handful of candidates took just one weekend, and the experiments also bore out the model's prediction of a distinct third phenotype.
Microsoft Research introduces Quine: a multimodal biology world model that prioritized compounds driving tumor-state shifts in pancreatic cancer, narrowing candidates in a single weekend
Microsoft Research introduces Quine, a research system combining a world model of biology trained jointly across modalities including sequence, structure, function, cellular state, and imaging with a harness connecting scientific tools, literature, the wet lab, and researchers; with the Broad Institute it used the system in pancreatic ductal adenocarcinoma (PDAC) to predict and prioritize thousands of compounds by their potential to shift tumor cells between therapeutically relevant states, wet-lab assays showed Quine's highest-ranked compounds produced the largest intended shifts, the whole process from narrowing the search space to prioritizing a handful of candidates took just one weekend, and the experiments also bore out the model's prediction of a distinct third phenotype.
Microsoft Research introduces Quine, a research system combining a world model of biology trained jointly across modalities including sequence, structure, function, cellular state, and imaging with a harness connecting scientific tools, literature, the wet lab, and researchers; with the Broad Institute it used the system in pancreatic ductal adenocarcinoma (PDAC) to predict and prioritize thousands of compounds by their potential to shift tumor cells between therapeutically relevant states, wet-lab assays showed Quine's highest-ranked compounds produced the largest intended shifts, the whole process from narrowing the search space to prioritizing a handful of candidates took just one weekend, and the experiments also bore out the model's prediction of a distinct third phenotype.
MIT News - Artificial intelligence Sep 29, 2026
In Philosophical Perspectives, MIT's Brian Hedden and Manish Raghavan systematically evaluate major objections to algorithmic monoculture—where one algorithm makes all decisions in a domain—arguing that objections such as systematic exclusion do not hold, proving mathematically that monoculture tends to create information echo chambers that hinder exploration, and showing through a series of hiring simulations that bundling algorithms into an "ensemble" can sometimes overcome this limitation so that monoculture performs as well as or better than polyculture.
In Philosophical Perspectives, MIT's Brian Hedden and Manish Raghavan systematically evaluate major objections to algorithmic monoculture—where one algorithm makes all decisions in a domain—arguing that objections such as systematic exclusion do not hold, proving mathematically that monoculture tends to create information echo chambers that hinder exploration, and showing through a series of hiring simulations that bundling algorithms into an "ensemble" can sometimes overcome this limitation so that monoculture performs as well as or better than polyculture.
MIT researchers systematically assess objections to algorithmic monoculture: systematic exclusion fails, but information echo chambers hinder exploration, and ensembling can partly offset it
In Philosophical Perspectives, MIT's Brian Hedden and Manish Raghavan systematically evaluate major objections to algorithmic monoculture—where one algorithm makes all decisions in a domain—arguing that objections such as systematic exclusion do not hold, proving mathematically that monoculture tends to create information echo chambers that hinder exploration, and showing through a series of hiring simulations that bundling algorithms into an "ensemble" can sometimes overcome this limitation so that monoculture performs as well as or better than polyculture.
In Philosophical Perspectives, MIT's Brian Hedden and Manish Raghavan systematically evaluate major objections to algorithmic monoculture—where one algorithm makes all decisions in a domain—arguing that objections such as systematic exclusion do not hold, proving mathematically that monoculture tends to create information echo chambers that hinder exploration, and showing through a series of hiring simulations that bundling algorithms into an "ensemble" can sometimes overcome this limitation so that monoculture performs as well as or better than polyculture.
发表出处待核验 Sep 29, 2026
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
Punching Bag local testbed shows six IPv6 target generation algorithms differ on scan budgets, aliased-prefix recognition, and response-rate adaptation
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
Communicable diseases intelligence (2018) Sep 29, 2026
Using weekly Google Trends search volumes for 2018 and 2019 compared against weekly influenza notifications from Australia's National Notifiable Disease Surveillance System (NNDSS), the study fitted four supervised regression models (elastic net, support vector regression, random forest, and feedforward neural network) independently for each state and territory except the Australian Capital Territory, for nowcast and one- and two-week-ahead predictions, finding that search volumes correlate with reported influenza rates over time, that random forest and elastic net generally performed better than the other models, that every modelled jurisdiction except the Northern Territory and Tasmania had at least two search queries with moderate to strong Pearson correlation with influenza notificatio
Using weekly Google Trends search volumes for 2018 and 2019 compared against weekly influenza notifications from Australia's National Notifiable Disease Surveillance System (NNDSS), the study fitted four supervised regression models (elastic net, support vector regression, random forest, and feedforward neural network) independently for each state and territory except the Australian Capital Territory, for nowcast and one- and two-week-ahead predictions, finding that search volumes correlate with reported influenza rates over time, that random forest and elastic net generally performed better than the other models, that every modelled jurisdiction except the Northern Territory and Tasmania had at least two search queries with moderate to strong Pearson correlation with influenza notificatio
Google search data plus machine learning forecast weekly influenza counts across Australian states, with best-model correlation from -0.353 to 0.977
Using weekly Google Trends search volumes for 2018 and 2019 compared against weekly influenza notifications from Australia's National Notifiable Disease Surveillance System (NNDSS), the study fitted four supervised regression models (elastic net, support vector regression, random forest, and feedforward neural network) independently for each state and territory except the Australian Capital Territory, for nowcast and one- and two-week-ahead predictions, finding that search volumes correlate with reported influenza rates over time, that random forest and elastic net generally performed better than the other models, that every modelled jurisdiction except the Northern Territory and Tasmania had at least two search queries with moderate to strong Pearson correlation with influenza notificatio
Using weekly Google Trends search volumes for 2018 and 2019 compared against weekly influenza notifications from Australia's National Notifiable Disease Surveillance System (NNDSS), the study fitted four supervised regression models (elastic net, support vector regression, random forest, and feedforward neural network) independently for each state and territory except the Australian Capital Territory, for nowcast and one- and two-week-ahead predictions, finding that search volumes correlate with reported influenza rates over time, that random forest and elastic net generally performed better than the other models, that every modelled jurisdiction except the Northern Territory and Tasmania had at least two search queries with moderate to strong Pearson correlation with influenza notificatio
bioRxiv Sep 29, 2026
On a four-way mood and psychosis classification task over 1,520 subjects from three studies and 14 acquisition sites, the work shows that marginal split-conformal calibration reached 0.9000 empirical coverage against a nominal 0.90 while healthy controls were covered at 0.941 and schizoaffective disorder at 0.818, and that class-conditional (Mondrian) calibration reduced this 12.3-point disparity to 0.4 points at a cost of 0.07 labels in mean set size (under 3%), making set size at matched coverage interpretable as a property of the subject and separating subjects into confident, boundary, ambiguous and unresolved strata, with the proportion independently flagged as label-ambiguous by a structural-MRI model rising monotonically across these strata (34.1%, 57.3%, 68.1%, 81.8%; p = 8.8e-18).
On a four-way mood and psychosis classification task over 1,520 subjects from three studies and 14 acquisition sites, the work shows that marginal split-conformal calibration reached 0.9000 empirical coverage against a nominal 0.90 while healthy controls were covered at 0.941 and schizoaffective disorder at 0.818, and that class-conditional (Mondrian) calibration reduced this 12.3-point disparity to 0.4 points at a cost of 0.07 labels in mean set size (under 3%), making set size at matched coverage interpretable as a property of the subject and separating subjects into confident, boundary, ambiguous and unresolved strata, with the proportion independently flagged as label-ambiguous by a structural-MRI model rising monotonically across these strata (34.1%, 57.3%, 68.1%, 81.8%; p = 8.8e-18).
In four-way mood and psychosis classification across 1,520 subjects, class-conditional (Mondrian) calibration cut the between-diagnosis coverage gap from 12.3 points to 0.4 points at a cost of 0.07 labels in mean set size
On a four-way mood and psychosis classification task over 1,520 subjects from three studies and 14 acquisition sites, the work shows that marginal split-conformal calibration reached 0.9000 empirical coverage against a nominal 0.90 while healthy controls were covered at 0.941 and schizoaffective disorder at 0.818, and that class-conditional (Mondrian) calibration reduced this 12.3-point disparity to 0.4 points at a cost of 0.07 labels in mean set size (under 3%), making set size at matched coverage interpretable as a property of the subject and separating subjects into confident, boundary, ambiguous and unresolved strata, with the proportion independently flagged as label-ambiguous by a structural-MRI model rising monotonically across these strata (34.1%, 57.3%, 68.1%, 81.8%; p = 8.8e-18).
On a four-way mood and psychosis classification task over 1,520 subjects from three studies and 14 acquisition sites, the work shows that marginal split-conformal calibration reached 0.9000 empirical coverage against a nominal 0.90 while healthy controls were covered at 0.941 and schizoaffective disorder at 0.818, and that class-conditional (Mondrian) calibration reduced this 12.3-point disparity to 0.4 points at a cost of 0.07 labels in mean set size (under 3%), making set size at matched coverage interpretable as a property of the subject and separating subjects into confident, boundary, ambiguous and unresolved strata, with the proportion independently flagged as label-ambiguous by a structural-MRI model rising monotonically across these strata (34.1%, 57.3%, 68.1%, 81.8%; p = 8.8e-18).
发表出处待核验 Sep 29, 2026
The study introduces a privacy measurement suite for synthetic network traffic spanning membership inference, data extraction, and network-specific attacks on identifiers, attributes, and topology, and evaluates four representative generators (NetShare, NetDiffusion, TrafficLLM, NetSSM) across five datasets, finding that even with black-box-only attackers and minimal training, membership inference reaches up to 0.88 TPR at FPR≤0.01 and up to 100% of network identifiers can be recovered, while anonymization and DP noise each cover only part of the risk at a utility cost.
The study introduces a privacy measurement suite for synthetic network traffic spanning membership inference, data extraction, and network-specific attacks on identifiers, attributes, and topology, and evaluates four representative generators (NetShare, NetDiffusion, TrafficLLM, NetSSM) across five datasets, finding that even with black-box-only attackers and minimal training, membership inference reaches up to 0.88 TPR at FPR≤0.01 and up to 100% of network identifiers can be recovered, while anonymization and DP noise each cover only part of the risk at a utility cost.
Four network-traffic generators leak their training data: membership inference reaches 88% TPR and network identifiers can be fully recovered
The study introduces a privacy measurement suite for synthetic network traffic spanning membership inference, data extraction, and network-specific attacks on identifiers, attributes, and topology, and evaluates four representative generators (NetShare, NetDiffusion, TrafficLLM, NetSSM) across five datasets, finding that even with black-box-only attackers and minimal training, membership inference reaches up to 0.88 TPR at FPR≤0.01 and up to 100% of network identifiers can be recovered, while anonymization and DP noise each cover only part of the risk at a utility cost.
The study introduces a privacy measurement suite for synthetic network traffic spanning membership inference, data extraction, and network-specific attacks on identifiers, attributes, and topology, and evaluates four representative generators (NetShare, NetDiffusion, TrafficLLM, NetSSM) across five datasets, finding that even with black-box-only attackers and minimal training, membership inference reaches up to 0.88 TPR at FPR≤0.01 and up to 100% of network identifiers can be recovered, while anonymization and DP noise each cover only part of the risk at a utility cost.
发表出处待核验 Sep 29, 2026
The authors built an automated detection system combining lexical URL filtering, dynamic rendering, OCR-based extraction, and content classification, applied it to 6,094,475 public URLs collected from VirusTotal, URLScan.io, Hybrid Analysis, the Wayback Machine, and RedHunt paste sites, and identified 12,331 potential exposures across authentication, financial, personal, and document-related categories, including 26 live password-reset links, 83 API keys, 12 publicly accessible e-signature workflows, 7 fully visible 2FA backup codes, and 62 JWTs lacking expiration constraints.
The authors built an automated detection system combining lexical URL filtering, dynamic rendering, OCR-based extraction, and content classification, applied it to 6,094,475 public URLs collected from VirusTotal, URLScan.io, Hybrid Analysis, the Wayback Machine, and RedHunt paste sites, and identified 12,331 potential exposures across authentication, financial, personal, and document-related categories, including 26 live password-reset links, 83 API keys, 12 publicly accessible e-signature workflows, 7 fully visible 2FA backup codes, and 62 JWTs lacking expiration constraints.
Researchers scanned 6.09 million public URLs and found 12,331 potential sensitive-data leaks, including 26 live password-reset links and 62 non-expiring JWTs
The authors built an automated detection system combining lexical URL filtering, dynamic rendering, OCR-based extraction, and content classification, applied it to 6,094,475 public URLs collected from VirusTotal, URLScan.io, Hybrid Analysis, the Wayback Machine, and RedHunt paste sites, and identified 12,331 potential exposures across authentication, financial, personal, and document-related categories, including 26 live password-reset links, 83 API keys, 12 publicly accessible e-signature workflows, 7 fully visible 2FA backup codes, and 62 JWTs lacking expiration constraints.
The authors built an automated detection system combining lexical URL filtering, dynamic rendering, OCR-based extraction, and content classification, applied it to 6,094,475 public URLs collected from VirusTotal, URLScan.io, Hybrid Analysis, the Wayback Machine, and RedHunt paste sites, and identified 12,331 potential exposures across authentication, financial, personal, and document-related categories, including 26 live password-reset links, 83 API keys, 12 publicly accessible e-signature workflows, 7 fully visible 2FA backup codes, and 62 JWTs lacking expiration constraints.
bioRxiv Sep 29, 2026
This work presents the first investigation, to the authors' knowledge, of the detectability of computationally modified sequences: the authors generate modified 16S rRNA sequences via random substitutions that pass the SILVA database quality-control inclusion criteria, and build classifiers that distinguish them from natural 16S rRNA using conserved motifs, with the best classifier achieving over 90% sensitivity and specificity on the testing set at a 5% artificial mutation rate, and one feature, gapped k-mers built from universally conserved nucleotides, conserved across all three domains of life despite relying on exact matches to patterns found in E. coli.
This work presents the first investigation, to the authors' knowledge, of the detectability of computationally modified sequences: the authors generate modified 16S rRNA sequences via random substitutions that pass the SILVA database quality-control inclusion criteria, and build classifiers that distinguish them from natural 16S rRNA using conserved motifs, with the best classifier achieving over 90% sensitivity and specificity on the testing set at a 5% artificial mutation rate, and one feature, gapped k-mers built from universally conserved nucleotides, conserved across all three domains of life despite relying on exact matches to patterns found in E. coli.
Researchers use conserved-motif classifiers to separate randomly substituted 16S rRNA from natural sequences, exceeding 90% sensitivity and specificity at a 5% mutation rate
This work presents the first investigation, to the authors' knowledge, of the detectability of computationally modified sequences: the authors generate modified 16S rRNA sequences via random substitutions that pass the SILVA database quality-control inclusion criteria, and build classifiers that distinguish them from natural 16S rRNA using conserved motifs, with the best classifier achieving over 90% sensitivity and specificity on the testing set at a 5% artificial mutation rate, and one feature, gapped k-mers built from universally conserved nucleotides, conserved across all three domains of life despite relying on exact matches to patterns found in E. coli.
This work presents the first investigation, to the authors' knowledge, of the detectability of computationally modified sequences: the authors generate modified 16S rRNA sequences via random substitutions that pass the SILVA database quality-control inclusion criteria, and build classifiers that distinguish them from natural 16S rRNA using conserved motifs, with the best classifier achieving over 90% sensitivity and specificity on the testing set at a 5% artificial mutation rate, and one feature, gapped k-mers built from universally conserved nucleotides, conserved across all three domains of life despite relying on exact matches to patterns found in E. coli.
发表出处待核验 Sep 29, 2026
The authors introduce GateScope, a lightweight black-box auditing framework that uses only public APIs to evaluate LLM API gateways along response content, multi-turn conversation consistency, billing accuracy, and latency characteristics; controlled validation on official endpoints yields an average F1 of 0.968±0.085 across 24 models, and auditing 10 commercial gateways reveals identification rates as low as 13.09% for gpt-5, degraded multi-turn memory checkpoints, a 62.8% billing gap for o*ey on gpt-4o, and markedly higher latency variation for b*ie.
The authors introduce GateScope, a lightweight black-box auditing framework that uses only public APIs to evaluate LLM API gateways along response content, multi-turn conversation consistency, billing accuracy, and latency characteristics; controlled validation on official endpoints yields an average F1 of 0.968±0.085 across 24 models, and auditing 10 commercial gateways reveals identification rates as low as 13.09% for gpt-5, degraded multi-turn memory checkpoints, a 62.8% billing gap for o*ey on gpt-4o, and markedly higher latency variation for b*ie.
GateScope black-box audits 10 commercial LLM API gateways: some identify gpt-5 as the claimed model only 13.09% of the time, and o*ey bills 62.8% above expected
The authors introduce GateScope, a lightweight black-box auditing framework that uses only public APIs to evaluate LLM API gateways along response content, multi-turn conversation consistency, billing accuracy, and latency characteristics; controlled validation on official endpoints yields an average F1 of 0.968±0.085 across 24 models, and auditing 10 commercial gateways reveals identification rates as low as 13.09% for gpt-5, degraded multi-turn memory checkpoints, a 62.8% billing gap for o*ey on gpt-4o, and markedly higher latency variation for b*ie.
The authors introduce GateScope, a lightweight black-box auditing framework that uses only public APIs to evaluate LLM API gateways along response content, multi-turn conversation consistency, billing accuracy, and latency characteristics; controlled validation on official endpoints yields an average F1 of 0.968±0.085 across 24 models, and auditing 10 commercial gateways reveals identification rates as low as 13.09% for gpt-5, degraded multi-turn memory checkpoints, a 62.8% billing gap for o*ey on gpt-4o, and markedly higher latency variation for b*ie.
bioRxiv Sep 29, 2026
The authors developed SpatialTRACE, comprising graph- and image-based models: SpatialTRACE-Graph combines gene-expression profiles with spatial neighborhoods to predict crypt-villus and epithelial-distance axis coordinates and to identify Peyer's patches in mouse small-intestine sections using as few as 10 annotated training villi, while SpatialTRACE-Image, a multiscale vision transformer that learns from the coordinate and region predictions generated by SpatialTRACE-Graph, predicts the same anatomical axis coordinates and regions across entire tissue images from DAPI alone and was applied to immunofluorescence images to map antigen-specific P14 CD8 T cells responding to acute systemic LCMV Armstrong infection in the small intestine, showing that a retinoic acid receptor inhibitor-treated
The authors developed SpatialTRACE, comprising graph- and image-based models: SpatialTRACE-Graph combines gene-expression profiles with spatial neighborhoods to predict crypt-villus and epithelial-distance axis coordinates and to identify Peyer's patches in mouse small-intestine sections using as few as 10 annotated training villi, while SpatialTRACE-Image, a multiscale vision transformer that learns from the coordinate and region predictions generated by SpatialTRACE-Graph, predicts the same anatomical axis coordinates and regions across entire tissue images from DAPI alone and was applied to immunofluorescence images to map antigen-specific P14 CD8 T cells responding to acute systemic LCMV Armstrong infection in the small intestine, showing that a retinoic acid receptor inhibitor-treated
SpatialTRACE extends sparse annotations into tissue-wide anatomical axis and region maps and predicts the same coordinates from DAPI images alone
The authors developed SpatialTRACE, comprising graph- and image-based models: SpatialTRACE-Graph combines gene-expression profiles with spatial neighborhoods to predict crypt-villus and epithelial-distance axis coordinates and to identify Peyer's patches in mouse small-intestine sections using as few as 10 annotated training villi, while SpatialTRACE-Image, a multiscale vision transformer that learns from the coordinate and region predictions generated by SpatialTRACE-Graph, predicts the same anatomical axis coordinates and regions across entire tissue images from DAPI alone and was applied to immunofluorescence images to map antigen-specific P14 CD8 T cells responding to acute systemic LCMV Armstrong infection in the small intestine, showing that a retinoic acid receptor inhibitor-treated
The authors developed SpatialTRACE, comprising graph- and image-based models: SpatialTRACE-Graph combines gene-expression profiles with spatial neighborhoods to predict crypt-villus and epithelial-distance axis coordinates and to identify Peyer's patches in mouse small-intestine sections using as few as 10 annotated training villi, while SpatialTRACE-Image, a multiscale vision transformer that learns from the coordinate and region predictions generated by SpatialTRACE-Graph, predicts the same anatomical axis coordinates and regions across entire tissue images from DAPI alone and was applied to immunofluorescence images to map antigen-specific P14 CD8 T cells responding to acute systemic LCMV Armstrong infection in the small intestine, showing that a retinoic acid receptor inhibitor-treated

Page 31 · showing 10