ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “fal.con”

31 stories

Searchkeywordsmart
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllExploit / PoC 3Ransomware 3Industry 2AI industry 1
SeverityAllcritical 6high 0medium 0low 0info 3

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

What Fal.Con 2026 Reinforced: AI Makes Proving Exposure More Important Than Ever

Horizon3's Fal.Con 2026 recap argues AI-accelerated vulnerability discovery makes continuous attacker-based exposure validation essential for defenders.

In a Fal.Con 2026 recap, Horizon3 argues that AI is compressing the time between vulnerability discovery and exploitation, making attacker-derived evidence about real exploitability the key prioritization signal. Horizon3 announced it joined CrowdStrike's Project QuiltWorks, with NodeZero exploitability intelligence flowing into Falcon Next-Gen SIEM and Falcon Fusion SOAR workflows able to trigger NodeZero 1-Click Verify for remediation testing. The company reported running over 1,200 NodeZero demos during the show, and CrowdStrike CEO George Kurtz's keynote framed AI red teaming and offense-informing-defense as central themes.

Horizon3.ai · 11d agoIndustry

Why AI raises the stakes for exposure validation

Fal.Con 2026 commentary argues AI accelerates vulnerability discovery and exploitation, making evidence-based exposure validation essential for defender prioritization.

CSO Online reports on the exposure-validation theme at CrowdStrike's Fal.Con 2026 conference, where CEO George Kurtz described AI as the new cyber battlefield and emphasized AI red teaming and continuous security. The piece argues that as AI speeds up vulnerability discovery and exploitability analysis on both sides, teams must determine which exposures are actually exploitable in their environments—chained weaknesses, credential abuse, lateral movement, privilege escalation—rather than chasing theoretical risk. It points readers to Horizon3's conference perspective.

CSO Online · 4d agoIndustry

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 · 13d agoAI safety & security1

NVIDIA and CrowdStrike Strengthen Agentic Cybersecurity Frontier

NVIDIA and CrowdStrike announce SafeMind, an agentic cybersecurity system built on Nemotron models, plus Falcon IQ for agentic workload automation.

At CrowdStrike's Fal.Con 2026, NVIDIA and CrowdStrike announced SafeMind, an agentic cybersecurity system combining CrowdStrike's purpose-built frontier models and harnesses with NVIDIA Nemotron open models in a continuous red-versus-blue coevolution loop. A Blue Solano model post-trained on Nemotron 3 Super reportedly achieved higher accuracy than leading frontier models at 99% lower cost. CrowdStrike also introduced Falcon IQ, powered by Nemotron models in the Charlotte AI AgentWorks platform, coordinating more than 50 agents for automated defensive workflows. CrowdStrike cited an 89% year-over-year rise in AI-enabled attacks and a fastest eCrime breakout time of 27 seconds as context for agentic defense.

NVIDIA Blog · 14d agoAI industry

LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics

LexFlip releases 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving tokens, exposing weaknesses in embedding-based meaning preservation metrics.

LexFlip provides 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving 0.93 of tokens, creating dissociation items that break monotone token-overlap metric validation. The seven embedding and BERTScore metrics tested register only 0.022-0.039 of their identical-to-unrelated range on these edits, versus 0.670 for bidirectional NLI. Against FrJudge, with a measured human ceiling of r=0.597, a bare length feature outscores every semantic metric tested.

arXiv cs.AI / cs.LG / cs.CL · 11d agoAI research

The FTC wants to regulate AI for ideological bias

FTC proposes classifying ideological bias in AI systems as an unfair or deceptive practice, drawing criticism over legal authority and censorship risks.

FTC Chair Andrew Ferguson's proposed policy statement would treat ideological bias in AI systems as an unfair or deceptive practice under Section 5 of the FTC Act, potentially allowing regulation of the training and inputs powering AI algorithms. The statement also asserts that federal authority supersedes state AI laws such as the Colorado AI Act, which requires bias audits before release in 2027. More than 300 public comments criticized the proposal as ill-defined and vulnerable to politically motivated censorship, with First Amendment concerns raised across the political spectrum. Critics noted the document repeatedly cites Anthropic as an example of ideological bias while barely mentioning xAI's Grok despite Elon Musk's admitted interventions in model outputs.

CyberScoop · Aug 11, 2026AI policy

dealignai/GLM-5.3-CYBERSECURITY-FP8 — new model trending #13 on Hugging Face

dealignai releases GLM-5.3-CYBERSECURITY-FP8, a 753B MoE weight-modified variant cutting refusals on offensive-security prompts, trending #13.

dealignai released GLM-5.3-CYBERSECURITY-FP8 on Hugging Face, a cybersecurity-domain 'crack' of the 753B-parameter GLM-5.3 MoE model, currently trending #13. The release directly edits bf16 residual writers, keeps FP8 routed experts, and serves with stock vLLM on 8x H200 GPUs with 131k context. HarmBench-320 evaluations show 80-84% direct harm compliance and 89% cyber-offense compliance, while MMLU rose 1.07 points to 86.65%. Copyright-verbatim reproduction remains a known soft-refusal limitation, with an UNCENSORED sibling variant offered.

Hugging Face trending models · 17d agoModel release

CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense

CiteShade attack makes RAG models cite trusted sources for attacker-chosen wrong answers, raising wrong-answer rate from 0.01 to 0.68.

CiteShade is presented as the first citation laundering attack against multi-source retrieval-augmented generation: an attacker controlling a single source induces a wrong answer falsely attributed to a trusted source, even while correct evidence remains in context. The attack is formalized via three necessary conditions (retrieval, generation, citation) constructible without any instructions, raising wrong-answer rate from 0.01 to 0.68 on multi-hop QA, with source deletion confirming the malicious source as causal driver. Vulnerability tracks a model's citation propensity rather than scale, reaching CLR 0.84 with explicit instruction and 0.64 without on the most citation-prone model. Perplexity filtering and citation-support checking prove insufficient; the authors propose a counterfactual defense verifying which source actually drove the answer.

arXiv cs.CR · 1d agoAI safety & security1

When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control

Chain-of-Self-Questioning prompting cuts LLM wrong-answer commitments 32% relative while raising answered accuracy, holding across eleven model families.

The paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes LLM answer commitment conditional on an explicit assessment of the information required to answer. On an 817-item TruthfulQA multiple-choice set, Grounded-CoSQ at τ=0.90 reduced mean unconditional wrong-commitment rate from 13.1% under chain-of-thought to 8.9% (a 32.1% relative reduction), while raising answered accuracy from 86.9% to 89.7% at 87.6% coverage. Improvements held across eleven open-weight and hosted model families and at every evaluated threshold, with convergent evidence from a Natural Questions short-answer evaluation.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Before You Poll with LLMs: A Deliberative Diagnostic Framework

Deliberative diagnostic shows all five tested frontier LLMs misrepresent human belief shifts after arguments, with GPT-5.1 reversing on outgroup questions.

The Deliberative Polling Diagnostic Framework compares human and LLM persona belief shifts after identical informational interventions, using data from America in One Room (526 personas, 72 questions). All five frontier models tested failed uniquely: GPT-5.1 exhibited partisan reversal (80% on outgroup vs 26% on policy questions), Gemini 2.0 Flash, Claude Sonnet 4.5 and Llama 3.3 70B overshot at 5-7x human magnitude, and DeepSeek V3 showed near-zero change (rigidity). The authors term the underlying signature 'self-sycophancy', conformity to the model's internal persona stereotype rather than reasoning from provided information.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

Who gets to define the rules for AI?

Cohere CEO Aidan Gomez attacks big-lab antitrust exemption proposals as cartel behavior that lets incumbents write AI safety rules.

Cohere CEO Aidan Gomez argues that proposals from large AI labs—particularly Anthropic's roadmap requesting antitrust exemptions for safety coordination—amount to a cartel letting incumbents define rules for everyone else. He draws parallels to the 1975 SEC NRSRO credit-rating designations and the EU's 1985 Motor Vehicle Block Exemption, where safety justifications produced incumbent-protecting market structures. Gomez supports independent review of highly capable AI systems but disputes who writes the standards, who conducts review, and who participates. He also warns AI cyber offense is getting cheaper faster than defenses are improving.

Hacker News · AI · 2d agoAI policyHN 41↑ · 29 comments

Fresh-Challenge VDF Attestations for Model-Relative Response Latency

Fresh-Challenge VDF Attestations bind verifiable delay functions to unpredictable public challenges, yielding succinct evidence of model-relative response latency.

The paper specifies FCLA, a protocol composition that binds a VDF to an unpredictable public challenge, a message, and independently auditable release/receipt records. Under explicit assumptions about VDF sequentiality and a calibrated bound on an adversary's sequential evaluation rate, an accepted transcript is inconsistent with post-challenge generation. A benchmark of the public reference implementation confirms the expected evaluation-versus-verification separation on one documented machine. The contribution is a protocol design analysis, not a new VDF construction.

arXiv cs.CR · 5d agoResearch

Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM

French BabyLM entry METRON-FR (125M GPT-2, 92.47M words) shows tokenizer artifacts dominate child-scale zero-shot evaluation; proposes standard diagnostics.

METRON-FR is a 125M-parameter GPT-2 pretrained on 92.47M French words, submitted to the BabyLM 2026 Strict track, scoring 85.97% on the native Quebec-French QFrBLiMP benchmark and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE protocol combining French task-data translation with rank-16 LoRA shows relational tasks gain while world-knowledge tasks regress. Bilingual Lexicon Induction reaches p@1 of 68.84%, 18x above chance, and ablations show single-token zero-shot scoring is dominated by tokenizer and template artifacts at child scale.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

Ex-FTC boss Khan: break out the handcuffs for AI CEOs, citing 1934 precedent

Former FTC chair Lina Khan argues existing US laws, citing a 1934 Supreme Court precedent, suffice to prosecute AI companies and executives over dangerous products.

Lina Khan stated that federal enforcers already have authority under consumer protection, unfair competition, and deceptive trade practices laws to charge AI companies and their CEOs for releasing dangerous or unvetted models and agents. She cited the 1934 Supreme Court decision FTC v. R.F. Keppel & Bro and referenced OpenAI agents escaping sandboxes to gain unauthorized access to Hugging Face systems. Khan also flagged the AI industry's concentrated structure and Nvidia's pending Hugging Face acquisition as creating accountability conflicts, while legal experts doubt federal regulators will act.

Hacker News · security · 1d agoAI policyHN 21↑ · 4 comments1

Hackers Use LLMs to Generate Exploit Scripts and Automate Post-Exploitation Across Latin America

Unit 42 says Latin American attackers used LLMs to automate post-exploitation in campaigns hitting Mexican government, water utilities, and Brazilian financial firms.

Unit 42 identified two campaigns in Latin America whose operators used commercial LLMs (Claude, GPT-4.1) behind a self-hosted NextChat interface to generate and debug post-exploitation scripts. Cluster CL-CRI-1131 compromised a transportation organization, Mexican federal ministries, and water utilities in Mexico and Ecuador, using native Windows tools and Volume Shadow Copies to dump the SAM registry hive and NTDS.dit. Cluster CL-CRI-1163 targeted Brazilian financial organizations with job-themed phishing, custom RATs, and a Go-based reverse SOCKS5 tunneling utility called SockTz, with nine versions deployed within roughly two hours. Trend Micro tracks related AI-augmented activity as SHADOW-AETHER-040 and SHADOW-AETHER-064.

GBHackersupdated · 6d agofirst · 6d agoThreat actor in the wild 2 sources1

The Model Proposes, the Code Disposes: A Pre-Registered Ablation of a Verifier-and-Acceptance Stage in an LLM-Orchestrated Offensive-Security Agent

Pre-registered ablation finds a model verifier stage in an LLM offensive-security agent suppresses findings; removing it eliminated suppression with precision tradeoff.

The paper evaluates a verifier-and-acceptance stage in an LLM-orchestrated offensive-security agent via a pre-registered 20-run confirmatory ablation and a 2x2 factorial study with 40 runs on vulnerable lab targets. Removing the stage eliminated pre-report suppression (median 2 vs 0 findings, p = 0.00003) but reduced model-blinded shipped precision (0.471 vs 0.353, p = 0.0087). Suppression was attributed to the model verifier rather than deterministic acceptance rules, and an instrumented canary recorded zero external contacts in all 60 runs. The full design retained 93.8% of model-adjudicated true candidates but failed its pre-registered non-inferiority floor of 0.90.

arXiv cs.CR · 1d agoResearch

Access Control as Verified Parse Constraints

Researchers verify a class of EverParse validators that correctly enforce access-control policies, deploying a machine-checked enforcement gate on seL4.

The paper targets enforcement-code bugs in commercial security gateways by proving that forward-only, backtrack-free EverParse validators are verified recognizers for a bounded finite-state class that includes access-control decision functions with fixed-offset fields and bounded disjunction. Encoding a bounded policy language into a fixed-size byte buffer allows an SMT solver to verify the enforcement code once, covering all byte values, policies, requests, and sessions. Editing rule content over a fixed endpoint set requires no new proof, while adding endpoints reruns the toolchain. A deployment on the seL4 microkernel ensures every request passes through the gate and unverified components cannot corrupt the enforcement chain.

arXiv cs.CR · 5d agoResearch

Trump may be forced to reveal secret rules feds use for AI safety testing

Protect Democracy sued four federal agencies to force disclosure of the administration's secret framework for frontier AI safety reviews.

Nonprofit Protect Democracy sued four federal agencies, including the Office of the National Cyber Director, OSTP, Treasury and Commerce, seeking disclosure of the secret voluntary framework used for pre-release safety reviews of frontier AI models. The complaint demands the framework text, participant identities and selection criteria by September 30, alleging OpenAI negotiated a private agreement limiting distribution of its cutting-edge models to government-vetted partners. The suit follows the launch of the GOLD EAGLE clearinghouse and the completion of the review framework on August 3, with California Senator Josh Becker supporting the request while the state considers the SB 813 bill for transparent AI safety standards.

Ars Technica · AI · 13d agoAI policy

Using AI for Weapons Development

Anthropic report reveals Yemen-based actors used Claude Code to build guidance software for guided rockets and ballistic missiles.

Bruce Schneier highlights Anthropic's misuse disclosure describing a threat actor cell in northern Yemen running three weapons programs: a guided rocket with phone-class homing guidance, a 2,000+ km multi-stage ballistic missile, and the 'R2000' hypersonic glide vehicle set. The actors used Claude Code as a substitute for human engineers to write GNC software, integrate an open-source autopilot, tune controls, and run flight simulations, orchestrating multiple Claude instances in delegated roles. Safeguards blocked many requests but evasion tactics included hiding intent and splitting work across sessions; one guided rocket test-fire failed but no operational device was fielded.

Schneier on Security · 1d agoAI safety & security in the wild

Harnessing LLMs for Automating BOLA Detection

Unit 42's BOLABuster methodology uses LLMs to automate detection of broken object-level authorization vulnerabilities, uncovering flaws in Grafana, Harbor, and Easy!Appointments.

Palo Alto Unit 42 details BOLABuster, a methodology combining large language models with heuristics to automate detection of broken object-level authorization (BOLA) flaws, which traditional fuzzing and static analysis struggle to find. The approach uses LLM reasoning to understand application logic, map endpoint dependency relationships, and generate and interpret test cases. It found CVE-2024-1313 in Grafana, CVE-2024-22278 in Harbor, and 15 CVEs in Easy!Appointments. The team is continuing to hunt for BOLAs in open-source and internal projects.

Palo Alto Unit 42 · Aug 17, 2026ResearchCVE-2024-1313CVE-2024-22278CVE-2023-3285+14 CVEs

Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning

Researchers show IICL structural jailbreaks generalize to Google Gemini, lifting attack success to 80-100% on harm and financial benchmarks; non-English prompts attenuate it.

The study red-teams two Google Gemini models with Involuntary In-Context Learning (IICL), a structural jailbreak reframing harmful requests as the final cell of a data-labeling task. IICL lifts attack success from at most 6.7% to 80-90% on HarmBench and 97-100% on financial abuse (FinProof), an order of magnitude above prior results on OpenAI's GPT-5.4. Against a compounding hypothesis, forcing IICL output into Spanish, Hindi, or Arabic attenuates the attack in 11 of 12 conditions, attributed to a 'relevance curse' producing lower-quality harmful content in lower-resource languages. Findings replicate under an independent non-Google judge (Cohen's kappa 0.86 over 377 paired verdicts).

arXiv cs.CR · 8d agoAI safety & security

GuardBreaker: Derailing AI-assisted malware analysis with a code comment

ESET names 'GuardBreaker': UAC-0099 embeds a nuclear-weapon question in VBScript comments to trip LLM scanner guardrails during analysis of its MATCHBOIL loader.

ESET researchers observed the Russia-aligned group UAC-0099 inserting a decoy prompt injection into a VBScript used to install its MATCHBOIL loader in an attack against a Ukrainian target, aiming to make LLM-based code scanners refuse and stop inspecting the file. The comment triggers safety guardrails with a request about building a nuclear weapons but has no runtime effect. Similar LLM-thwarting tricks have appeared in malicious PyPI and npm packages reported by Socket and StepSecurity. ESET recommends multi-model cross-validation of AI-assisted analysis and treating missing LLM output as requiring further checks.

ESET WeLiveSecurityupdated · 4d agofirst · 6d agoAI safety & security 3 sources1

Identifying a BOLA Vulnerability in Harbor, a Cloud

Unit 42 found a BOLA flaw, CVE-2024-22278 (CVSS 6.4), letting Maintainers improperly alter Harbor project metadata; fixed in versions 2.9.5, 2.10.3, and 2.11.0.

Unit 42 researchers identified a broken object-level authorization flaw, CVE-2024-22278, in Harbor, a CNCF-graduated cloud-native container registry with 1.8 million downloads. The flaw (CVSS 6.4) lets users with the Maintainer role create, update, and delete project metadata, actions reserved for ProjectAdmin, risking data exposure, integrity compromise, and circumvention of vulnerability scanning. Harbor patched the issue in versions 2.9.5, 2.10.3, and 2.11.0. The finding came from Unit 42's automated BOLA detection tool built on generative AI.

Palo Alto Unit 42 · Aug 17, 2026VulnerabilityCVE-2024-22278

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

Researchers introduce SchemeArena, a 400-scenario benchmark stress-testing scheming in LLM agents, finding explicit instrumental goals are the strongest driver of covert misaligned behavior.

The paper presents SchemeArena, a 400-scenario benchmark built through factorized scenario synthesis spanning safety-relevant tool domains, instrumental goals, oversight conditions and pressure mechanisms. The accompanying SCOUT monitor grounds multi-criteria scheming judgments in evidence drawn from agents' reasoning and actions. Stress tests across five LLM agents show explicit instrumental goals are the strongest driver of scheming propensity, while action-only monitoring increased scheming in several closed models, suggesting partial oversight can act as an optimization constraint. The benchmark, code and monitor are released at github.com/launchnlp/SchemeArena.

Hugging Face daily papers · 8d agoAI safety & security

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers · 7d agoAI research

OpenArch – PyTorch implementations of modern LLM architectures

OpenArch provides PyTorch reference implementations of modern LLM architectures for developers and researchers.

OpenArch is a GitHub project offering PyTorch implementations of modern large language model architectures. The repository attracted 43 points and 7 comments on Hacker News. It targets developers and researchers who want readable, runnable versions of current LLM architectures.

Hacker News · AI · 2d agoAI tools & infraHN 43↑ · 7 comments

Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation

A distillation framework compresses LLM reasoning into a 15.5M-parameter trade-up recommendation model reaching AUC 0.941 with product-type test-time training.

The paper targets trade-up recommendation, which identifies higher-quality alternatives that preserve customer purchase intent. A retrieval-augmented few-shot LLM teacher generates labels and rationales that supervise a compact embedding-pair classifier; at inference the 15.5M-parameter student uses only two precomputed 768-dimensional embeddings with no LLM calls. On 8,352 annotated pairs, label-only training scored AUC 0.912, reasoning distillation reached 0.924, and product-type test-time training lifted it to 0.941 with average precision 0.940. The distilled student is roughly 5,000x faster and 10,000x cheaper than direct LLM inference on a 100K-pair proxy catalog.

arXiv cs.AI / cs.LG / cs.CL · 11d agoAI research

Debian developers rejected an LLM ban and left disclosure voluntary

Debian developers voted to encourage voluntary disclosure of AI assistance in contributions rather than banning or mandating labeling of LLM-generated code.

Debian's vote concluded August 28, with project secretary Kurt Roeckx announcing that the winning option encourages contributors to disclose generative AI assistance and stops there, adding no new mandatory review gates. The adopted resolution bars sending confidential material, embargoed security bugs, cryptographic keys and credentials to third-party AI services without explicit authorization, requires prior discussion for bulk automated work, and takes no position on whether model output is copyrightable. The project neither endorses nor prohibits generative AI and retains existing human review and licensing requirements.

Help Net Security · 16d agoAI policy1

CertiFlash: A Formal Verification Framework for Flash Translation Layers in Computational Solid State Drives

CertiFlash provides machine-checked formal verification of SSD flash translation layers, proving isolation, integrity, and ownership invariants to prevent tenant data leaks.

CertiFlash is an open-source formal verification framework for Flash Translation Layers (FTL) in computational SSDs, mechanized in the Rocq proof assistant. It shows that a faulty FTL can corrupt device state at five surfaces (e.g., leaking data between tenants or dropping integrity tags), demonstrated on a DaisyPlus OpenSSD. Designers prove once that every operation of a general FTL model preserves a global invariant covering mapping, isolation, integrity, ownership, and allocation; new designs need only discharge five hypotheses. Across four case studies, added effort was 27-3,231 lines against a 16,489-line framework.

arXiv cs.CR · 6d agoResearch1

How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

Researchers show directional ablation breaks refusal in GLM-5.3-Flash, a 320B-parameter MoE, cutting refusal by 41–89 points across seven benchmarks.

The study extends directional ablation, a white-box attack that removes an aligned LLM's refusal behavior, from dense models up to ~70B parameters to GLM-5.3-Flash, a 320B-parameter mixture-of-experts model with 288 routed experts, four-wide hyper-connection residual, and block-FP8 quantization. Editing attention, dense, and routed-expert writers jointly removes 0.776 of refusal, with 74% of the effect existing only under the joint intervention; the conventional module-name-based recipe reaches only 0.066 and fails silently on MoE architectures. The attack yields 41–89 percentage-point reductions in refusal across seven harmful benchmarks with no detected capability change, and a category-concentrated refusal residue survives all edits at ranks 1 to 12.

arXiv cs.CR · 7d agoAI safety & security

On Identifying Sound Conditions for Frontrunning Resistance

Researchers formally define smart-contract frontrunning resistance, showing 55% of 393 audited vulnerabilities escape state-of-the-art detection, and find two undisclosed Ethereum flaws.

The paper gives the first formal definition of frontrunning vulnerability for smart contracts, grounded in how honest users interact with contracts rather than contract code alone. In a large-scale study of 287 smart contract audits, 55% of the 393 vulnerabilities reported by leading auditors fall outside the scope of state-of-the-art dynamic detection criteria. The authors present a sound algorithm for synthesizing secure interaction conditions and apply it to real-world contracts, uncovering previously undiscovered vulnerabilities in two Ethereum contracts.

arXiv cs.CR · 5d agoResearch