Search: “reliability”

Your Agent Aced the Task. Will It Do It Again?

IBM Research Hugging Face post examines whether LLM agents that succeed at a task once will reliably succeed again.

Hugging Face published an IBM Research blog post titled 'Your Agent Aced the Task. Will It Do It Again?' with URL slug 'altk-evolve-consistency'. No article text was provided, but it appears to address agent consistency and reliability evaluation across repeated task runs. This is relevant to developers building or evaluating LLM agent systems.

Hugging Face Blog·Sep 15, 16:00 UTC · 18h agoAI tools & infra

Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation

Referee-Based Quality Estimation flags unreliable polyp segmentations at inference without ground truth, reaching ROC-AUC 0.960 with SegFormer-B0 referees.

RBQE measures agreement between a primary segmentation model and an independently trained referee on a 1,223-image external benchmark drawn from four public datasets. A cross-architecture SegFormer-B0 referee achieves the strongest signal (ROC-AUC 0.960), beating a Test-Time Augmentation baseline by 0.055 ROC-AUC under an identical protocol. Excluding trivially separable empty-mask cases, ROC-AUC falls to 0.876 (SegFormer-B0) and 0.783 (same-architecture control), but RBQE's margin over baselines widens. Progressive rejection of low-agreement predictions increases mean Dice of retained outputs, supporting selective prediction at the cost of one extra forward pass.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:32 UTC · 6d agoAI research

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

E2A-Bench, a 969-query financial chart reasoning benchmark, finds VLMs fail evidence-to-action consistency, with fine-tuning amplifying BUY:SELL bias 4-6x.

E2A-Bench is a 969-query benchmark built from 323 HS300 constituents across three input modalities with deterministic OHLCV-derived evidence anchors, evaluating grounding, reasoning-action consistency, evidence-confidence calibration, and directional coverage via UCR, RCI, ECI, and NDR metrics. Testing 20 VLMs showed the lowest-hallucination model ranked near the bottom on coverage with only 6.4% directional coverage, and oracle-aided verification reduced unsupported claims but could collapse coverage. Financial fine-tuning amplified the BUY:SELL ratio by factors of 4.21 to 4.68 across base-fine-tuned pairs.

Hugging Face daily papers·Sep 12, 20:00 UTC · 3d agoAI research

Introducing ChatGPT for Financial Services

OpenAI launches ChatGPT for Financial Services, pairing built-in market data with GPT-6 Astra for banking research workflows.

OpenAI introduced ChatGPT for Financial Services, a tailored ChatGPT Work experience shaped by design partners Morgan Stanley and Evercore, targeting investment banking and equity research. It bundles premium data from Daloopa, PitchBook, LSEG News, and Crunchbase hosted on OpenAI infrastructure with granular citations, optimized MCP connectors for S&P Global and FactSet, and 50+ connectors, plus planned entitlement integrations with S&P Capital IQ, LSEG, MSCI, Dow Jones Factiva, and Moody's. It runs GPT-6 Astra, which OpenAI claims is state of the art in information retrieval, financial reasoning, and artifact generation, and includes enterprise controls such as SAML SSO, SCIM, role-based access, and no default training on firm data.

OpenAI News·updated Sep 10, 18:25 UTC · 5d ago·first Sep 10, 07:00 UTC · 6d agoAI industry 3 sources

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

New framework tests whether LLM-cited explanation factors are necessary or sufficient, finding weak correlation across Claude, GPT, and Gemini models.

An arXiv paper introduces black-box intervention tests measuring whether factors LLMs cite in their explanations are necessary or sufficient for their outputs in agent oversight workflows. Across eight models from the Claude, GPT, and Gemini families, Spearman correlations between cited rankings and measured influence ranged from 0.349-0.354 (advisor recommendation) to 0.431-0.580 (prompt monitoring). Uncited factors scored above the lowest cited factor in up to 57.6% of advisor responses, showing cited top-three factors do not reliably identify the most influential inputs.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:37 UTC · 11d agoAI safety & security1

Linux Kernel ZcopyReaper Vulnerability Lets Local Attackers Gain Root Privileges

Linux kernel RDS zero-copy flaw CVE-2026-43502 (ZcopyReaper) lets unprivileged local users gain root; fix in 7.1-rc3, public PoC published.

CVE-2026-43502, dubbed ZcopyReaper, is a Linux kernel local privilege escalation flaw in the RDS zerocopy send path, present since kernel 4.17, allowing unprivileged local attackers to gain root. NebuSec researcher Yuan Tan demonstrated root escalation on openSUSE kernel 6.4.0-150600.23.100; the fix landed in commit 44b550d88b26 with Linux 7.1-rc3 the first patched mainline release. Exploitation requires CONFIG_RDS and CONFIG_RDS_TCP but not unprivileged user namespaces, and PoC exploit material is publicly released alongside more than 20 other exploitable 2026 kernel CVEs.

GBHackers·Sep 15, 08:18 UTC · 1d agoExploit / PoCCVE-2026-43502CVE-2026-43501CVE-2026-43074+4 CVEs

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark tests LLM health reasoning over longitudinal wearable data; the best of 14 evaluated LLMs reaches 72.9% accuracy.

WearableQA comprises 4,084 ten-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning. Evaluation of 14 proprietary and open-source LLMs shows performance from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:52 UTC · 11d agoAI research

AI is getting better at election facts, but voters shouldn’t rely on it

CyberScoop·Aug 5, 09:00 UTC · Aug 5, 2026Exploit / PoC in the wild

Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering

Evaluation of twelve LLMs on 222 clinical questions shows verbatim quotes rarely substantiate claims; claude-opus-5 fully substantiates only 37.1%.

The authors build a standardized harness over four clinical practice guidelines and evaluate twelve LLMs on 222 synthetic clinical questions, measuring citation attachment, verbatim quote production, and claim substantiation. Most models attach verbatim quotes to over 90% of claims from prompting alone, though lightweight models like claude-haiku-4.5 struggle. Quotes frequently fail to substantiate claims: claude-opus-5 quotes 98.0% of claims but fully substantiates only 37.1%, exposing a capability gap for verifiable clinical QA.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:53 UTC · 1d agoAI research

[AINews] 10% worse, 100x cheaper, 10000x faster: Why Simulation is taking over

Latent Space argues AI training pipeline stages—rewards, data, teachers, curricula, environments—are flipping from human-made to model-made simulation.

Latent Space's AINews essay traces how each component of AI training has turned synthetic since 2022: reward models (InstructGPT, RLAIF), synthetic pretraining data (Microsoft Phi, NVIDIA Nemotron-4 340B), model teachers (Alpaca, DeepSeek-R1 distillation), and self-generated curricula (Self-Rewarding Language Models, SPIN). In 2026 it highlights Karpathy's autoresearch loop—700 experiments yielding 20 kept improvements, cutting GPT-2 training time from 2.02 to 1.80 hours—and Z.ai's GLM-5.3 fully synthetic RL environment, judging, and verification stack. It frames these shifts as 'simulation': 10% worse but 100x cheaper and 10,000x faster than human equivalents.

Latent Space·Aug 22, 07:36 UTC · 25d agoAI industry

get the module working against several of the 12.4.3 versions

A Metasploit Framework exploit module was updated to work reliably against several 12.4.3 software versions.

A commit to the Rapid7 Metasploit Framework repository adjusts an existing exploit module so it functions against several 12.4.3 version targets. The change is described as getting the module working against those versions, indicating reliability or compatibility improvements. The commit text does not describe a new vulnerability, exploitation campaign, or affected victims.

Metasploit Framework commits·Sep 9, 11:10 UTC · 6d agoTools1

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Fortunate Recall introduces ontology-based lifecycle policies for LLM memory, cutting confabulation roughly in half (e.g., 45.1% to 22.4%) versus Mem0.

Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific lifecycle rules including differential temporal decay, slot-key supersession, event-time validity, and retrieval routing. FR-Bank scores 76.9% on the new 516-question LifecycleBench, ahead of Mem0, A-MEM, Memory-R1, and MemoryOS (61%-70.5%), and 75.2% on LongMemEval-S. End-to-end, confabulation drops from Mem0's 45.1% to 22.4% over answered queries, with the ranking replicating on open-weight Kimi K2.5 and transferring to the independent BEAM benchmark (46.8% vs 32.9%).

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:31 UTC · 6d agoAI research

Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing

A study of 180 US workers found each LLM phishing personalization level raised click-intention odds by 28%, but credibility depends on context fit.

The arXiv paper evaluates how personalized pretexts in LLM-generated spear phishing affect perceived credibility, using 180 US working adults across 1,436 evaluations of emails with four cumulative personalization levels, from workplace context to shared-project details. Convincingness rose 2.40 points per level in sensitivity analysis and click-intention odds increased 28% per level, while non-clickers shifted toward deleting rather than reporting. Qualitative coding showed details matching the recipient's role and routines supported credibility, whereas incorrect, vague, or channel-inappropriate details raised suspicion. The authors argue personalization effectiveness depends on pretext fit, with implications for workplace security training.

arXiv cs.CR·Sep 3, 19:21 UTC · 12d agoResearch

Senate Democrats introduce bill to distribute $300 million annually to shore up water system cybersecurity

The Record·Aug 10, 15:58 UTC · Aug 10, 2026Policy & legal

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark introduces 4,084 questions over real longitudinal wearable data, showing 14 LLMs score 19.6-72.9% on health reasoning, far from solved.

WearableQA is a benchmark of 4,084 10-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning, using a dual-grounding framework combining literature and population-validated patterns. Evaluations of 14 proprietary and open-source LLMs show accuracy ranging from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

Hugging Face daily papers·Sep 3, 20:00 UTC · 12d agoAI research

How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules

OpenAI profiles César de la Fuente's lab using ChatGPT and Codex alongside deep-learning models to accelerate antimicrobial molecule discovery.

OpenAI published a case study on bioengineer César de la Fuente's lab, which uses ChatGPT and Codex for hypothesis brainstorming, code writing, dataset processing, and bridging knowledge gaps across biology, chemistry, and computer science. The lab's deep-learning models scan genome and protein databases for antimicrobial peptide candidates, potentially cutting initial searches from years to hours. Bacterial antimicrobial resistance was associated with about five million deaths in 2021, a toll projected to roughly double by 2050.

OpenAI News·Sep 10, 16:00 UTC · 5d agoAI industry1

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

A self-distillation safety framework tunes narrow-boundary refusals in Qwen3-8B, raising target-domain refusal to 84.75% while cutting over-refusal from 15.20% to 5.20%.

The paper formulates narrow-boundary safety, where deployments need refusals within specific topics rather than whole subjects, and proposes an offline self-generated framework with controlled topic generation, escalating retries, and harmful-benign boundary pairs. On political persuasion with Qwen3-8B, the method raised target-domain refusal from 9.47% to 84.75% and cut the mean unsafe-response rate across three broader benchmarks from 26.26% to 0.14%. Verified target-model responses reduced over-refusal from 15.20% to 5.20%, and boundary-pair data cut comply-side over-refusal on held-out pairs from 32.94% to 4.16%. Results show data composition controls the safety-usability trade-off and alignment should be evaluated on both sides of the refusal boundary.

Hugging Face daily papers·Sep 2, 20:00 UTC · 13d agoAI safety & security1

The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet

Researchers counted 36,769 publicly reachable self-hosted AI endpoints, only about 2% behind HTTP authentication, exposing Ollama, vLLM, and Flowise to abuse.

A Mysterium VPN study found 36,769 self-hosted AI endpoints reachable through internet scanning, with only 2.02% returning an HTTP authentication challenge. Open WebUI accounted for 18,529 reachable instances, Ollama for 6,935 fingerprinted hosts, and 5,223 agent-builder and workflow platforms were exposed, often holding API keys, database credentials, and other secrets. The report highlights LLMjacking risk from exposed Ollama APIs, a critical Flowise bug (CVE-2026-40933), leaked n8n tokens, and prior SentinelOne/Censys research finding roughly 175,000 exposed Ollama hosts in 130 countries.

Security Affairs·Sep 11, 17:27 UTC · 4d agoAI safety & securityCVE-2026-409331

Toward an Empirical Probabilistic Risk Manifestation Model of Organizational Cybersecurity in SMEs

Empirical study of 22 SME security assessments builds a probabilistic risk model and shows assessments can be cut 24-45% while retaining most critical findings.

Researchers analyzed 281 validated security findings from 22 real-world SME cybersecurity assessments conducted over two years via a pro bono university clinic. They derived an empirical Risk Manifestation Model linking eight organizational security functions to two exposure conditions, five attack mechanisms, and six outcome categories, using probability propagation to identify dominant risk pathways. The dominant pathway runs from asset exposure to credential compromise to unauthorized access, stable under leave-one-organization-out analysis. Retaining six functions reduces assessment burden by 24% while preserving 97% of critical findings; five functions cut burden 45% while preserving 89% of critical findings.

arXiv cs.CR·Sep 14, 01:15 UTC · 2d agoResearch

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

SyncWorld is an action-conditioned world model acting as a zero-shot robotics simulator across unseen environments via visual calibration.

Researchers propose SyncWorld, an action-conditioned world model that simulates robot action outcomes in unseen environments without additional training. It uses a visual calibration episode of paired frames and actions to establish the setup-specific Action-Visual Mapping in context. Experiments show accurate simulation of action outcomes in novel settings and that simulated rollouts enable test-time policy improvement without training.

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

BenchMIRT: What are LLM benchmarks actually measuring?

AllenAI's BenchMIRT blog post examines what LLM benchmarks actually measure and their reliability.

AllenAI published a Hugging Face blog post introducing BenchMIRT, which investigates what large language model benchmarks actually measure. No article text is available, so specific findings, methods, or benchmark scores cannot be extracted. The work appears to target benchmark validity, a live concern for model evaluation and comparison.

Hugging Face Blog·Sep 1, 21:39 UTC · 14d agoAI research

Authorization Architectures for Tool-Using AI Agents

Review paper proposes an authorization reference architecture for tool-using AI agents, identifying runtime enforcement and delegation bounds as unresolved gaps.

This review examines authorization models for tool-using AI agents that invoke APIs, databases, browsers, and protocols like MCP, arguing every consequential agent action must be traceable to a human principal, bounded by delegation, and contestable. It introduces a principal hierarchy spanning human user, operator/deployer, orchestrator agent, sub-agent, and tool endpoint, and analyzes five layers including credential lifecycle, delegation propagation, runtime enforcement, prompt injection as authorization bypass, and auditability. Drawing on 89 primary sources from 2023-2026, it proposes seven structural requirements, a four-layer reference architecture, and three deployable configurations.

arXiv cs.CR·Sep 14, 17:21 UTC · 1d agoAI safety & security

Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment

Researchers audit 31 NLP techniques for clinician-annotated suicide risk prediction, finding only 5 of 31 comparisons yield reliable gains.

A study of 1,635 clinician-annotated social media posts ran roughly 300 controlled experiments across 7 methodological families, auditing techniques such as model scaling, synthetic data, ensembling, and threshold tuning under severe class imbalance. The proposed system reformulates risk factor prediction as entailment between posts and codebook definitions, using architecturally diverse ensembles with class-balanced training and deployment-consistent calibration. It scores 0.8203 for risk, 0.7953 for evidence, and 0.7045 macro-F1 for factors, ranking third among 53 teams.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:14 UTC · 8d agoAI research

ControlAI’s Connor Leahy on why superintelligence is ‘not a weapon, it’s an adversary’

ControlAI's Connor Leahy argues superintelligence is an unmanageable adversary, backs the Sanders-Casar 'Ban Superintelligence Act' and international verification agreements.

On TechCrunch's Equity podcast, ControlAI's US Executive Director Connor Leahy argued that alignment and containment alone cannot manage superintelligence risk and advocated halting frontier development, citing the Sanders-Casar 'Ban Superintelligence Act' and parallel UK legislation ControlAI advised on. He characterized frontier AI labs as political actors, pointed to the OpenAI-related Hugging Face breach as evidence of danger, and called AI self-improvement the point of no return, endorsing international 'trust but verify' agreements.

TechCrunch · AI·Sep 9, 15:50 UTC · 6d agoAI policy

A Ranking Approach for Measuring Calibration

Researchers propose rankECE, a ranking-based calibration error measure with theoretical guarantees that outperforms binned ECE approximations.

The paper introduces rankECE, an alternative to Expected Calibration Error (ECE) that measures miscalibration by comparing points with neighboring predicted-probability values. It addresses the impossibility of estimating ECE with guaranteed accuracy in assumption-free settings. Theoretical guarantees and empirical results establish rankECE as a better proxy for ECE than the binned approximations most commonly used in practice.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 17:34 UTC · 4d agoAI research1

Are Unreachable Nodes Truly Safe? Fully Eclipsing Monero's P2P Network!

Researchers present Nyx and Moros, the first eclipse attacks against Monero nodes behind NATs, requiring no inbound access and demonstrated on mainnet.

The paper presents the first eclipse attacks tailored to unreachable Monero nodes operating behind NATs, requiring no inbound access to the victim. The attacks poison the peerlists of reachable nodes, which relay contamination to unreachable nodes' whitelists, then exploit Monero's outbound connection refresh logic to evict benign neighbors and monopolize all outbound connections. Nyx achieves a complete, persistent eclipse of long-running unreachable nodes in large-scale SEED Emulator simulations, while Moros stealthily eclipses newly joined nodes during bootstrapping and was demonstrated on the Monero mainnet. Countermeasures are proposed.

arXiv cs.CR·Sep 9, 14:43 UTC · 6d agoResearch

What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.

The paper introduces a benchmark for revision propagation: when users request a local change, LLMs must identify dependencies and update all affected parts of an artifact generated through conversation, where context lives in the chat history. Nine revision methods, including sequential reflection and parallel sampling variants, were evaluated on gpt-oss-20b/120b, gpt-5.4-mini, and qwen3.5-9b/27b/122b. Baselines scored 68.3-93% accuracy, and selecting among three parallel samples via LLM-based or medoid selection improved accuracy by 2.2-9.7% as the most cost-effective test-time compute strategy. Code and dataset are released.

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

Security Incident – BGP Hijacking

Attackers BGP-hijacked Softaculous' Hetzner IP block for 33 hours, obtained valid TLS certificates, and delivered a malicious Virtualizor update to some servers.

Between August 28 and 30, 2026, AS62390 (NexonHost) announced 162.55.80.0/24 via transit AS6204 (Zet.net) without authorization, diverting traffic while retaining Hetzner's AS24940 on the AS path. The attacker obtained valid Let's Encrypt certificates for virtualizor.com domains because the CA's domain validation was also routed through the hijack, so affected connections showed no TLS warnings. A malicious Virtualizor update package reached a handful of installations; routing was fully restored, and reconstruction from RIPE RIS data showed all 368 collector peers carried the hijacked route at some point with roughly 28% time-weighted diversion.

Lobsters · security·Sep 3, 02:07 UTC · 13d agoData breach

When LLM judges agree, should we believe them?

Amazon ICML paper uses Ising models to correct correlated LLM-judge votes, beating accuracy-weighted panels by 9-14%.

Amazon Science describes an ICML paper, "Dependence-aware label aggregation for LLM-as-a-judge via Ising models," addressing how correlated judge outputs inflate majority-vote confidence. The unsupervised method models pairwise dependence between judges, learning both reliability and similarity without human reference labels. Tested on relevance, toxicity, and summarization tasks with 10 judge models at temperature zero, it outperformed accuracy-weighted voting by 9% to 14%.

Hacker News · AI·Sep 14, 16:29 UTC · 1d agoAI researchHN 41↑ · 23 comments

Microsoft’s September 2026 Patch Tuesday addresses 964 CVEs (CVE-2026-81963, CVE-2026-85880)

Microsoft's September 2026 Patch Tuesday fixes a record 964 CVEs, including two zero-days actively exploited in the wild.

Microsoft patched a record 964 CVEs in its September 2026 Patch Tuesday release, with 101 rated critical and 824 rated important, making it the largest Patch Tuesday to date. The release includes fixes for two zero-days that were exploited in the wild, with CVE-2026-81963 and CVE-2026-85880 highlighted in the release. Affected products span Windows core components, Office, Exchange, .NET, Visual Studio, Active Directory services (including AD CS and AD FS) and numerous Azure services. Tenable notes the release surpasses July's as the biggest ever.

Tenable Blog·Sep 8, 18:07 UTC · 7d agoVulnerability in the wildCVE-2026-81963CVE-2026-858801

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

A controlled study finds agent memory portability varies sharply: fixed-schema knowledge graphs survive model swaps while compressed notes degrade.

The study compares preserving an agent's history as raw long context, RAG chunks, compressed natural-language notes, or fixed-schema knowledge graphs across model upgrades, using 48 synthetic histories and two open-weight sub-10B-parameter models. Fixed-schema KG accuracy changed by only +0.0004 ± 0.0020 after a writer swap, while compressed NOTES shifted asymmetrically by +9.91 or -13.28 percentage points depending on migration direction. Mixed 50/50 embedding migrations captured only 4.96 of an 11.90-point RAG re-embedding gain; 80% of the NOTES deficit came from information lost at construction, and 81% of the RAG deficit from retrieval failures. Store-only repair of NOTES failed to reach 90% recovery in all 48 cases, while retaining raw histories enabled recovery in 34 of 48 for one direction.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:44 UTC · 11d agoAI research1

1.1.1.1 now supports post-quantum DNSSEC, all 2,420 bytes of it

Cloudflare's 1.1.1.1 resolver now validates post-quantum DNSSEC signatures using ML-DSA-44, a 2,420-byte NIST algorithm, preparing DNS for post-quantum migration by 2029.

Cloudflare enabled 1.1.1.1 to validate DNSSEC signatures using ML-DSA-44 (algorithm 18), a NIST-standardized post-quantum signature with 1,312-byte public keys and 2,420-byte signatures, roughly 38x larger than ECDSA P-256. The large signatures exceed common DNS-over-UDP limits, forcing fallback to TCP and creating downgrade risks while conventional algorithms must be published alongside. Cloudflare cites the risk of a quantum computer breaking RSA/ECDSA signatures by 2030 and plans full post-quantum security by 2029.

Cloudflare Blog·Sep 10, 13:00 UTC · 5d agoTools1

18 ways to check whether data can be trusted for AI

ETSI published TR 104 180 defining 18 data quality metrics, including fairness and privacy, to assess whether datasets are fit for AI.

ETSI's technical report TR 104 180 defines 18 metrics across four groups - intrinsic quality, usability and lineage, fairness, and privacy - each with calculation formulas, plus an open-source tool that scores datasets. Testing on an aircraft engine sensor dataset and a US census dataset revealed a roughly threefold gender gap in high earners (about 31% of men versus 11% of women) and two privacy failures: re-identification via age, race, sex, and country, and sensitive fields stored in plaintext. The working group included Sejong University, EGM, TTA, Daejeon University, and CNIT.

Help Net Security·Sep 7, 00:00 UTC · 9d agoAI policy

Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool

Researchers present SMART, an ML performance-modeling library regenerated by AI coding agents from natural-language design docs instead of code.

The paper describes SMART, a symbolic performance-modeling library whose main branch contains almost no code: the repository is a DAG of self-contained design documents, and coding sub-agents regenerate implementations from only the docs on version updates. Reliability rests on a worked-example doc style used as in-context demonstrations and a minimal operator IR with SymPy cost expressions, offering both fast analytical roll-up and fine-grained modulo-scheduling modes. Regenerated implementations reproduce hand-audited reference models, including DeepSeek-V3 serving on a TPU pod slice, to round-off precision.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:08 UTC · 11d agoAI research1

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

Tracking Elirks Variants in Japan: Similarities to Previous Attacks

Unit 42 links new Elirks backdoor variants attacking Japanese organizations to 2012 Taiwan attacks, delivered via spear-phishing PDFs exploiting Adobe Flash CVE-2011-0611.

Unit 42 analyzed new Elirks backdoor variants found in an attack on a Japanese business, noting strong similarities to 2012 attacks on Taiwanese ministries. The backdoor retrieves its C2 address from attacker-created accounts on Japanese blog and SNS services. Recent deliveries used an airline e-ticket lure named "E-TKT" with a PDF exploiting Adobe Flash CVE-2011-0611. Shared infrastructure and tactics with the Scarlet Mimic campaign suggest possible ongoing cyber espionage across East Asia.

Palo Alto Unit 42·Aug 17, 12:56 UTC · 29d agoThreat actor in the wildCVE-2011-0611

K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.

K-Bench is a clinician-calibrated, protected benchmark evaluating 125 model configurations from 33 base models across 14 providers on 200 multi-turn vignettes covering suicide, self-harm, domestic violence, substance misuse and no-risk presentations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible comparisons from 151 clinician-rated transcripts. Leading models combined supportive conversation with combined-risk scores above 95, while risk exploration varied substantially among weaker configurations; therapeutic prompting helped weaker models and elevated reasoning produced no average improvement. A continuously updated public leaderboard is hosted at k-bench.ai with protected test materials.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:49 UTC · 1d agoAI safety & security

What happens when AI agent governance is missing at scale

meshIQ engineering head Gourab Basu argues AI agent governance must inspect proposed tool calls in-flow, since prompts alone cannot control nondeterministic agents.

In a Help Net Security interview, Gourab Basu, Global Head of Engineering at meshIQ, argues that prompt instructions are an insufficient control boundary for nondeterministic AI agents. He advocates a framework-independent governance engine that inspects proposed tool calls and parameters before execution, citing an example of pausing refunds above $100 for human approval. He warns that scaling from ten to a thousand agents makes manual oversight and destination-side controls unworkable, so governance must sit inside the agent execution flow across frameworks such as FastMCP.

Help Net Security·06:00 UTC · 4h agoAI safety & security

Approval Integrity and Recovery in LLM Answer Publication

Study measures approval integrity in Lightcap LLM answer publication, finding the 14B response-act checker accepts 291 of 302 unsupported answers.

The study evaluates exact-content binding, authorization freshness, and checkpoint recovery in Lightcap's publication enforcement using 3,600 assessments over 900 human-annotated RAGTruth responses from three Ministral models. The production 14B response-act checker accepts 291 of 302 unsupported answers versus 41 for a direct-grounding baseline, with supported-answer retention of 95.2% versus 66.9%. A stateful recheck-recovery policy increases exact-match error by 9.23 percentage points relative to initial checkpoints, and controlled evidence-fingerprint changes expose asymmetric freshness enforcement between publication and recovery. A separate BIPIA prompt-injection experiment records zero target insertions among 266 valid editor outputs.

arXiv cs.CR·Sep 14, 13:48 UTC · 1d agoAI safety & security

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