Search: “benchmark-contamination”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale

VLoc Bench tests 27 language models at locating vulnerable files in 290 repositories; best system reaches 0.229 File F1 and 38.4% of tasks unsolved.

The Vulnerability Localization Benchmark (VLoc Bench) contains 500 real-world vulnerabilities from 290 repositories across six package ecosystems and 147 CWE categories, pairing pre-fix and post-fix repository snapshots. Agents receive only a CWE description and read-only terminal access to identify affected files, and must confirm absence on patched snapshots. The strongest of 27 language models and four static-analysis tools achieves just 0.229 File F1; 38.4% of tasks receive no correct localization, and effective localizers still report unsupported locations on patched repositories.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:44 UTC · 1d agoAI research

50

SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

SWE-Bench Pro Verified is a corrected benchmark showing prior coding-agent scores were inflated by reward hacking and flawed tasks.

Analysis of SWE-Bench Pro found its evaluation undermined by reward hacking from leakage of gold solutions or hidden evaluation information, plus task quality issues such as misleading problem statements and improperly scoped tests. The authors present SWE-Bench Pro Verified, combining anti-hacking safeguards that eliminate major leakage channels with minimal task refinements. Evaluations show some models perform substantially worse than previously reported, suggesting SWE-Bench Pro overestimates real software engineering capability.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research1

35

Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks

Audit of eight cybersecurity LLM benchmarks shows evaluation pipeline choices can swing scores by over 80 points and reshuffle most model rankings.

Researchers modeled eight cybersecurity benchmarks as configurable measurement pipelines and audited 10 proprietary, open-weight, and cybersecurity-specialized LLMs. They identified 15 systematic failure modes and showed a single pipeline choice can change a model's score by more than 80 percentage points and alter rankings; semantically similar task pairs rank the same models differently. Under a standardized harness, nine of 10 models shifted at least three ranks on at least one benchmark, motivating pipeline-aware auditing for reliable model evaluation.

arXiv cs.CR·Sep 8, 14:01 UTC · 7d agoAI research1

42

Towards Standardized Evaluation of GPU Memory Safety with GMSBench

GMSBench provides 149 CUDA tests covering spatial, temporal, and concurrency GPU memory errors, exposing detection gaps in Compute Sanitizer.

GMSBench is a GPU memory safety benchmark comprising 149 self-contained CUDA tests spanning spatial, temporal, and concurrency errors across different GPU memory spaces and execution scenarios. The authors evaluate NVIDIA's Compute Sanitizer across multiple GPU architectures using the suite, exposing gaps in its detection coverage. The benchmark offers a standardized foundation for comparative evaluation of GPU memory safety mechanisms.

arXiv cs.CR·Sep 8, 15:11 UTC · 7d agoResearch

28

What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking

First systematic robustness benchmark of five local invisible image watermarking methods across 55 transformations finds all are vulnerable, with inpainting and geometric misalignment completely breaking payload…

The paper presents the first systematic robustness benchmark for local invisible image watermarks, covering 55 image transformations across signal distortions, coordinate alignment changes, indirect local edits, and direct watermark edits. It evaluates five methods: MaskWM, WAM, OmniGuard, TrustMark, and PixelSeal, all supporting localization natively or with minimal adaptation. Results show every method is vulnerable to some transformation; MaskWM offers the strongest payload recovery and localization but the lowest clean-image quality, and synchronization further improves its recovery under geometric transformations. Geometric misalignment and generative local edits such as inpainting and outpainting can completely impair payload recovery, while signal distortions are often tolerated.

arXiv cs.CR·Sep 15, 08:30 UTC · 1d agoResearch

42

PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

PIDS-Bench shows prompt-injection detectors scoring F1 above 0.98 still misclassify about one-third of external benign security-adjacent prompts, revealing provenance-sensitive over-defense.

PIDS-Bench is a frozen multi-axis benchmark that jointly evaluates prompt-injection detectors on attack detection and benign false-positive behavior at fixed thresholds, spanning in-distribution inputs, hard-benign prompts, obfuscated attacks, and domain/structural distribution shifts. It evaluates seven detectors plus a rule-based lower-bound reference. A detector exceeding F1 = 0.98 on held-out data still misclassifies roughly one-third of an externally-sourced benign security-adjacent subset, and no internal detector reaches F1 >= 0.95 with hard-benign FPR <= 0.10 on the stress distribution. Hard-negative augmentation nearly eliminates over-defense on curated stress inputs but leaves it intact on externally-sourced prompts, a pattern termed provenance-sensitive over-defense.

arXiv cs.CR·Sep 14, 04:28 UTC · 2d agoAI safety & security

38

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

Introduces VEX-Bench, 75 expert-labeled real-world cases testing whether LLM agents can assess supply chain vulnerability exploitability; frontier models reach about 80% F1.

VEX-Bench is the first benchmark evaluating LLM agents on assessing whether upstream dependency vulnerabilities are exploitable in downstream projects, with 75 real-world expert-labeled cases across Python, Java, and Go mined from GitHub. Nine models across three agent harnesses were evaluated; GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, but only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. The gap highlights the difficulty of moving beyond binary exploitability calls to explaining exploitability reasons, unlike prior benchmarks targeting zero-day settings.

arXiv cs.CR·Sep 7, 22:52 UTC · 8d agoResearch1

42

Testing race conditions with memory access tracing and stack-based delay injection

Google Project Zero released MAccConc, Linux kernel tooling that traces memory accesses to explore and test race condition interleavings.

A Google Project Zero researcher published MAccConc (Memory Access Concurrency), tooling for exploring possible interleavings of multithreaded test cases in the Linux kernel, available on GitHub. The tools use KCOV with ASAN outline-mode instrumentation to record per-access memory traces, enabling automatic testing of all A-B-A interleavings plus terminal and GUI explorers for manual analysis. The work targets confirming race condition candidates, building reliable regression tests, and enabling concurrency fuzzing, drawing on ideas from SKI and Ned Williamson's sockfuzzer.

Google Project Zero·Sep 8, 07:00 UTC · 8d agoResearch1

48

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Benchmark Radar provides a living searchable database of 1,283 AI benchmark records and 12,916 score observations drawn from 37 daily discovery sources.

Benchmark Radar combines daily discovery of benchmark papers, repositories, datasets, and releases from 13 direct connectors and 24 first-party feeds into a searchable catalog with model card mentions and score histories. The catalog contains 1,283 source records drawn from 4 benchmark catalogs plus 12,916 numeric observations on 790 records. The release includes a web dashboard with leaderboard, Pareto frontier of score versus usage, saturation and trend views, daily feeds, a CLI, and reproducible analysis. The paper audits the full catalog and examines benchmark saturation and limits of score comparisons.

Hugging Face daily papers·Sep 9, 20:00 UTC · 6d agoAI research

25

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.

VDiff-Bench is a multiple-choice benchmark of 1,756 four-way questions over image pairs covering 10 change categories including position, motion, color, texture, OCR/text and illumination, with curated hard negatives. Evaluation of 11 state-of-the-art open- and closed-source MLLMs shows fine-grained visual comparison remains brittle: 7-8B-scale open-source models score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture. Notably, Grok 4.3 shows a sharp performance drop on noise and texture differences, falling behind large open-source models like Kimi K2.5 and K3.

Hugging Face daily papers·Sep 4, 20:00 UTC · 11d agoAI research

32

AWS puts AI vulnerability detection to the test, and false positives pile up

AWS publicly released its Deception Benchmark (14,822 samples) showing leading AI models falsely flag 41-99% of safe code as vulnerable.

AWS released its Deception Benchmark publicly, containing 14,822 samples across 16 programming languages and more than 70 CWE categories, with 9,695 scored samples split into 6,988 code-level and 2,707 environment-gated challenges. AWS evaluated 12 models from five providers using single-turn prompts and found none met its production bar of below 10% for both false-positive and false-negative rates. With direct prompting, models caught nearly all real vulnerabilities but incorrectly flagged 41% to 99% of safe code, with precision between 52% and 71%. Asking models to prove exploitability reduced false positives by 17 to 74 percentage points but raised false-negative rates to 7-44%, with models struggling most when external controls like Kubernetes Network Policies blocked apparent exploits.

Help Net Security·Sep 14, 04:00 UTC · 2d agoAI research

55

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark with 660 instances measures whether LLMs can spot and fix underspecified research-method details for faithful implementation.

Researchers introduce IdeaAMBIG, a benchmark of 660 evidence-grounded instances (163 real-world gaps from reproducibility reports and GitHub issues, 497 controlled synthetic gaps) built from papers, codebases, and reproduction artifacts. It evaluates codification-readiness assessment, defect localization, and clarification action generation. Across 13 LLMs, the best model achieved only 9.6% Macro Defect Recovery Rate on real-world instances but 80.6% clarification success when given the annotated defect. An oracle study showed gold resolutions raise the codification-ready rate from 14% to 98%, identifying defect localization as the main bottleneck.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:59 UTC · 6d agoAI research2

28

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark of 660 specification-gap instances shows LLMs localize implementation-critical research gaps poorly, with best model at 9.6% defect recovery.

IdeaAMBIG is a benchmark of 660 evidence-grounded instances evaluating whether research-method specifications provide enough information for faithful implementation: 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps. It tests codification-readiness assessment, defect localization, and clarification action generation across 13 LLMs. The best model achieves only a 9.6% Macro Defect Recovery Rate on real-world instances, though 80.6% clarification success when given the annotated defect, and an oracle study shows gold resolutions raise codification-ready rates from 14% to 98%. Defect localization emerges as the main bottleneck across all evaluated models.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research

30

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

BenchShield uses lifecycle-model-backed instrumentation to detect reward hacking in LLM-agent benchmarks, lifting full-chain recall to 77-100% at up to 65% lower cost.

The framework grounds reward-hacking detection in a finite lifecycle model of an evaluation's reward-relevant events, combining a static phase-aware taint analysis with runtime infrastructure-side evidence attribution. Evaluation used a human-labeled corpus of 456 adjudicated trajectories drawn from more than 31,000 public agent runs across three benchmarks. BenchShield improves full-chain recall from 23-94% to 77-100% and same-vector coverage from 16-56% to 43-78%, cuts per-task cost by up to 65%, and achieves 96% accuracy detecting reward hacking at runtime.

arXiv cs.CR·Sep 10, 03:10 UTC · 6d agoAI safety & security1

42

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.

Researchers built an evaluation framework from 400 BigCodeBench problems with injected AST-level corruptions, each with a known minimal patch, to measure over-editing in LLM code repair. Even strong models like GPT-5.5 produce unnecessarily large edits despite high Pass@1. Adding a preservation instruction reduced average excess Levenshtein distance from 0.195 to 0.131, cut added cognitive complexity by 26.6%, and raised Pass@1 by 2.3 points. Reinforcement learning post-training gave the best out-of-domain edit-fidelity trade-off, while supervised fine-tuning overfit to seen corruption patterns.

Hugging Face daily papers·Sep 2, 20:00 UTC · 13d agoAI research1

30

Measuring benchmark optimization in speech recognition

Hugging Face examines how much speech recognition systems overfit benchmarks and how to measure benchmark optimization in ASR.

A Hugging Face post on measuring benchmark optimization in automatic speech recognition, analyzing how model improvements on benchmarks reflect genuine capability gains versus overfitting. It is evaluation methodology research with no direct security impact.

Hugging Face Blog·Aug 21, 00:00 UTC · 26d agoAI research

22

[0day-rubbish] core-admin 1.0.164 (build 16468) Systemic shell command injection via ineffective quote escaping (8.8)

0day Rubbish discloses a CVSS 8.8 shell command injection in core-admin 1.0.164 via ineffective quote escaping, enabling authenticated remote code execution.

0day Rubbish Research Team publicly disclosed a systemic shell command injection (CWE-78) in core-admin 1.0.164 (build 16468). The flaw stems from ineffective quote escaping and scores 8.8 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H). The disclosure does not mention a CVE identifier or observed exploitation in the wild.

Full Disclosure·Sep 8, 17:31 UTC · 7d agoVulnerability1

38

"They don't care about this": A Systematic Study of TEE Build Reproducibility in the Wild

91% of 115 surveyed TEE deployments across Intel SGX, TDX, and AMD SEV fail to provide reproducible builds needed for verifiable remote attestation.

A systematic study of 115 TEE deployments found 91% were not reproducible and 80% lacked both source code and a reference build, undermining remote attestation guarantees. Interviews with 12 developers of 50 Intel SGX projects confirmed that only one participant treats reproducibility as a development priority. The authors identify technical barriers such as embedded timestamps plus ecosystem-level issues like lack of build-environment control in multi-stakeholder projects, and call for holistic, committed reproducibility practices.

arXiv cs.CR·Sep 10, 11:43 UTC · 6d agoResearch

38

Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities

SWEADV benchmark shows adversarial issue descriptions make LLM program-repair agents write insecure fixes in 51.7% of cases, evading most detection tools.

Researchers built SWEADV, a benchmark of 750 adversarial issue descriptions derived from 150 SWE-bench Verified repair tasks, covering command execution, deserialization, path traversal, denial of service, and weak hashing attack types. Tested on mini_swe agents backed by GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R, adversarial descriptions induced malicious behavior with successful repair in 51.7% of cases. Detection was weak: LLM-as-judge pre-repair screening reached only 62.3% accuracy, and post-repair detection via static analysis and LLM-as-judge achieved just 39.4% and 55.4%.

arXiv cs.CR·Sep 14, 17:53 UTC · 1d agoAI safety & security1

52

Compiler Can Undo Your Security Checks

Chris Domas explains at Black Hat how legal compiler optimizations can strip security checks and memory-clearing operations, turning secure C source into vulnerable binaries.

David Bombal interviews researcher Chris Domas at Black Hat USA 2026 about how the C abstract machine permits compilers to legally transform code in ways that remove security protections, delete memory-clearing operations, and introduce time-of-check to time-of-use vulnerabilities. Factors like register pressure, structure layout, and data size affect vulnerability, with examples where 17 or 33 byte buffers are safe while nearby sizes produce vulnerable code. An AI-assisted analysis of 500 million lines of open-source code identified 300 potentially dangerous patterns. Recommended mitigations include enabling compiler warnings, using sanitizers, analyzing optimized builds, and testing the exact binary that ships.

Hacker News · security·Sep 12, 14:07 UTC · 3d agoResearchHN 22↑ · 27 comments

48

Feature Recovery for Object Understanding After Irreversible Fire Damage

TRACE benchmark with 21.4K scenes studies post-fire object understanding; a Feature Recovery Module improves degraded-image retrieval by 12.5% and material recovery by 20.1%.

The paper introduces TRACE, a transformation-aware benchmark with 21.4K real-image-grounded synthetic scenes, 499 object identities across 189 categories, and five tasks covering degraded-object detection, pristine-state recovery, material recovery, description generation, and functional reasoning. Existing models degrade sharply: RF-DETR mAP falls 71% relative from least to most severe level, and InternVL3.5 retrieval R@1 drops from 93.85 to 28.11. The proposed Feature Recovery Module maps degraded encoder features to pristine-aligned representations while keeping the host model frozen, averaging relative gains of 12.5% for retrieval and 20.1% for material recovery across VLM hosts and severity levels.

Hugging Face daily papers·Sep 9, 20:00 UTC · 6d agoAI research

30

An Empirical Analysis of ReDoS Vulnerabilities and ReDoS Detection Tools

Study of NVD data finds ReDoS vulnerabilities growing more prevalent and more likely to be exploited, while five detection tools disagree substantially.

The study compares five publicly available ReDoS detection tools and one regex correction tool across three datasets. An empirical analysis of all ReDoS vulnerabilities reported to the NVD finds they are becoming more prevalent and are much more likely to be exploited than non-ReDoS weaknesses. The detection tools exhibited substantial disagreement on whether a given regex is vulnerable.

arXiv cs.CR·Sep 9, 15:09 UTC · 6d agoResearch

35

OPEN-1B: A Fully Auditable Training Run

Open-1B releases a 1B-parameter model with bitwise-reproducible training, letting independent auditors verify every step of the run on commodity hardware.

The paper introduces a 'fully auditable' tier of model transparency: every training operation is reproducible with bitwise certainty on heterogeneous commodity hardware by imposing definite ordering on GPU kernel reductions, data batch ordering, and collective communication. Because replaying a full run on one machine is infeasible, a collective verification scheme lets many independent auditors certify individual steps covering the whole run. The authors release Open-1B with its full pretraining dataset, every intermediate checkpoint, the training codebase, and an audit harness. This rules out undisclosed data, injected biases, or backdoors that proof-of-learning or proof-of-training-data techniques cannot exclude.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:23 UTC · 19h agoAI research

58

Forging Tree-Ring: Reproducing and Instrumenting Black-Box Semantic Watermark Forgery

Reprompt watermark forgery reproduces on Stable Diffusion XL using free-tier T4 GPUs, with forged images accepted by the genuine detector 5 of 6 times.

The authors reproduce the Reprompt forgery attack of Müller et al. against Tree-Ring watermarking on Stable Diffusion XL using the released code on free-tier dual T4 GPUs with 14.6 GB usable memory, versus the A40 hardware of the original study. Over six trials, the genuine detector flagged genuine images 6/6, clean images 0/6, and forged images 5/6, at 325-332 seconds per attack. They also recovered the detector's discarded non-central chi-square statistic and built two natural scores separating forged images from the clean null at AUC 0.861 and 0.972. The notebook, pinned fork, and all measurement artifacts are released with the paper.

arXiv cs.CR·Sep 11, 14:35 UTC · 4d agoResearch

30

1Password's AI patching benchmark is misleading

Trail of Bits reanalysis says 1Password's 26% AI clean-fix rate is misleading; 86% of eligible patches blocked exploits.

Trail of Bits critiques 1Password's FLAWED AI patching benchmark, arguing its 26% clean-fix headline mixes trials where agents were instructed to apply wrong fixes (22% of data) with trials that prohibited compiling or testing (36%). Restricting to reasonable conditions, 2,634 of 3,067 patches (86%) blocked the supplied exploit. Trail of Bits also reports 12.5% of 2,265 developer first fixes failed in its own 2024-2026 assessments, and released post-patch-validation and review-walkthrough agent skills.

Lobsters · security·Sep 15, 20:03 UTC · 16h agoResearch

45

PIA-Bench: Towards Automated Privacy Impact Assessment with Large Language Models

Researchers release PIA-Bench, the first open benchmark evaluating how accurately LLMs can automate privacy impact assessments using 73 curated federal PIAs.

PIA-Bench is the first open benchmark for evaluating large language models on real-world privacy impact assessments (PIAs). The authors audited 499 expert-authored PIAs published by US federal agencies and curated 73 structured PIAs comprising 451 privacy risk items and 831 mitigation items. Off-the-shelf LLMs were found to produce meaningful assessments while identifying clear avenues for improvement. The paper calls for domain-specific LLM agent workflows, accountable LLM infrastructure, and new quality standards for PIAs.

arXiv cs.CR·Sep 11, 08:16 UTC · 5d agoResearch1

48

Recreating Minecraft Is Not a Benchmark

Opinion piece argues viral demos like one-prompt Minecraft recreations are overfit 'demo-benchmarks' measuring preparation, not true model capability.

The author argues that fixed, famous demo tasks (Minecraft builds, SVG pelicans) are trivially optimizable by labs each release cycle, so they no longer differentiate model capability. The piece cites Thinking Machines' Inkling Small scoring within a point of its flagship on the Artificial Analysis Intelligence Index with less than a third of the parameters, and beating it on Humanity's Last Exam, GPQA Diamond, and SciCode. The proposed alternative is rotating or holdout evals such as LiveBench, ARC-AGI's private set, and held-back portions of Humanity's Last Exam.

Hacker News · AI·Sep 6, 14:52 UTC · 9d agoAI researchHN 73↑ · 71 comments

45

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Researchers propose auditing LLM bias via relative hidden-state representations, detecting bias increases with 3-50x less compute than output-level benchmarks.

The paper introduces a reference-based bias auditing method that compares hidden-state representations across model variants, such as before and after fine-tuning, by encoding sentences relative to a fixed anchor set. The resulting Representational Bias Shift (Delta-B) correlates with output-level bias change in 15 of 18 tested settings, reaching |r| = 0.84 under full fine-tuning across WildGuardMix, DecodingTrust, and ToxiGen benchmarks. Thresholding Delta-B detects checkpoints whose bias increased with ROC AUC between 0.65 and 0.99 and beats a SEAT-based baseline, while auditing a model in about three minutes with 3-50x less compute.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research

42

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard benchmark shows LLM code-generation guardrails fail widely, with ~50% jailbreak ASR text-to-code and up to 100% code-to-code.

Researchers introduce CS-Guard, the first systematic benchmark for evaluating LLM guardrails for code generation security, covering text-to-code (1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack) and code-to-code (331 prompts across infilling, completion, and translation). They evaluate 9 guardrails across seven LLMs, finding average jailbreak attack success rates around 50% for text-to-code and 14.4% to nearly 100% for code-to-code. The fictional scenario attack achieves ASR close to 100% across many guardrails, raising reliability concerns for real-world software development. The benchmark and data are released publicly.

arXiv cs.CR·Sep 9, 06:50 UTC · 7d agoAI safety & security1

45

ZDI-26-636: Oracle Outside In Technology PostScript File Parsing Heap-based Buffer Overflow Remote Code Execution Vulnerability

ZDI disclosed a heap-based buffer overflow in Oracle Outside In Technology's PostScript parsing (CVE-2026-60412) enabling user-triggered remote code execution.

Zero Day Initiative published ZDI-26-636, a CVSS 7.8 heap-based buffer overflow in PostScript file parsing within Oracle Outside In Technology. Remote attackers can execute arbitrary code when the target opens a malicious file or visits a malicious page, making user interaction a requirement. The vulnerability is tracked as CVE-2026-60412. The advisory reports no exploitation.

ZDI Published Advisories·Sep 9, 05:00 UTC · 7d agoVulnerability 4 sourcesCVE-2026-604121

22