ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “safety-eval”

27 stories

Searchkeywordsmart
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAll
SeverityAllcritical 0high 0medium 0low 0info 0

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

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackersupdated · 5d agofirst · 5d agoThreat actor in the wild 3 sources1

Acronis cPanel Backup Plugin Vulnerability Exploited in Targeted Attacks

Acronis warns CVE-2026-87886, a local privilege escalation flaw in its cPanel/WHM and Plesk backup plugins, is exploited in targeted attacks.

Acronis disclosed CVE-2026-87886 (CVSS 7.8), a high-severity local privilege escalation caused by insecure file permissions in its Backup plugin for cPanel & WHM and Backup extension for Plesk on Linux. Affected versions include cPanel & WHM plugin builds before 1.9.3.1021 (fixed in 1.9.3 HF3) and Plesk extension builds before 1.8.11.638. A low-privileged attacker could escalate permissions and potentially run arbitrary code, impacting confidentiality and integrity of the application. Acronis says exploitation has been detected in the wild in limited, targeted attacks, but has not identified the attackers, timing, or objectives.

The Hacker News · 4h agoExploit / PoC in the wild 6 sourcesCVE-2026-87886

CVE-2026-85484: HTML::FormHandler versions before 0.410002 for Perl render option group labels and radio button labels into HTML without escaping

HTML::FormHandler before 0.410002 for Perl renders option group and radio button labels unescaped into HTML, enabling XSS (CVE-2026-85484).

Robert Rothenberg disclosed CVE-2026-85484 on the oss-security mailing list, affecting HTML::FormHandler versions before 0.410002 for Perl. The module renders option group labels and radio button labels into HTML without escaping, which can enable cross-site scripting in applications using the rendered markup. The issue is addressed in version 0.410002.

oss-security · 7d agoVulnerability 2 sourcesCVE-2026-85484

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

Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety

Unit 42 research shows LLM safety refusals concentrate in a thin neural layer, motivating external, multi-layered AI security controls.

Palo Alto Networks Unit 42 introduces Perturbation Probing, a diagnostic technique for measuring the fragility of LLM safety mechanisms. The research finds that safety refusal behavior is localized within a thin neural layer, implying small perturbations can undermine built-in refusals. The authors argue this motivates external, multi-layered security defenses on top of model-internal safety training.

Palo Alto Unit 42 · 18d agoAI safety & security

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

TIER benchmark shows LLM safety behaviors shift gradually across threat implicitness levels, with jailbreaks exposing the largest robustness gaps.

The TIER benchmark evaluates LLM safety behaviors across four risk domains and four threat levels, from explicit harmful requests to sophisticated jailbreaks, using a six-label behavior scale and two independent LLM judges. Experiments on six open-weight LLMs show safety behaviors evolve gradually across threat levels rather than flipping from refusal to compliance. Models with similar Attack Success Rates can exhibit distinct response distributions, arguing for behavior-aware safety evaluation.

arXiv cs.CR · 12d agoAI safety & security

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

Study shows training LLMs on refusal rationales instead of boilerplate refusal statements reduces false refusals while maintaining safety performance.

The paper decomposes safety-tuning responses into a boilerplate refusal statement and an explanatory rationale, finding that refusal statements push models to rely on superficial cues and misjudge benign queries as harmful. Training solely on rationales reduces false refusals while maintaining comparable safety performance, and the benefits carry over to in-context learning configurations and remain compatible with inference-time mitigations. The results argue for precisely curated, fine-grained safety supervision datasets when aligning LLMs.

Hugging Face daily papers · 12d agoAI safety & security1

HazardAuditor: From Executable Threats to Safer Computer-Use Agents

HazardAuditor trains execution-grounded guard models for computer-use agents, improving safety verdict accuracy by up to 16.5 points.

HazardAuditor runs heterogeneous agents (Claude Code, Codex, Hermes, OpenClaw) in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision. It introduces Guard Policy Optimization (GuardPO), which converts deterministic safety outcomes into sequence-level advantages and normalizes rationale and verdict regions so the safety decision becomes the effective optimization unit. Across multiple benchmarks and heterogeneous computer-use systems, HazardAuditor improves accuracy by up to 16.5 percentage points over the strongest prior guard model. Code, models, and evaluation artifacts are being released.

Hugging Face daily papers · 2d agoAI safety & security

CVE-2026-85485: HTML::FormHandler versions before 0.410002 for Perl render some error messages into HTML without escaping

HTML::FormHandler before 0.410002 for Perl renders error messages into HTML unescaped, enabling cross-site scripting (CVE-2026-85485); fixed in 0.410002.

Robert Rothenberg disclosed CVE-2026-85485 on the oss-security mailing list, affecting HTML::FormHandler versions before 0.410002 for Perl. The module renders some error messages into HTML without escaping, which can enable cross-site scripting in applications using its rendered output. The issue is fixed in version 0.410002.

oss-security · 7d agoVulnerability 2 sourcesCVE-2026-854851

CVE-2026-86304: MojoX::Authentication versions before 0.006 for Perl allow SAML authentication bypass because parse_assertion builds Net::SAML2::Binding::POST without a trust anchor

MojoX::Authentication before 0.006 for Perl allows SAML authentication bypass because parse_assertion builds Net::SAML2::Binding::POST without a trust anchor (CVE-2026-86304).

CVE-2026-86304 affects MojoX::Authentication versions before 0.006 for Perl. The parse_assertion function builds Net::SAML2::Binding::POST without a trust anchor, so SAML assertions are not validated against a trusted signing key, enabling authentication bypass. The flaw is fixed in version 0.006 of the module.

oss-security · 9d agoVulnerabilityCVE-2026-86304

USN-8736-1: Perl vulnerabilities

Ubuntu issued USN-8736-1 fixing two Perl regex flaws that could cause denial of service, code execution, or security-restriction bypass.

Ubuntu released a security notice addressing two Perl vulnerabilities in regular expression handling. CVE-2026-15534 involves mishandling of large inputs during regex matching, enabling out-of-bounds heap reads or writes that could lead to denial of service or arbitrary code execution. CVE-2026-19487 involves incorrect matching for regexes with alternative branches, allowing security restrictions to be bypassed. Users are advised to apply the updated packages.

Ubuntu Security Notices · 8d agoAdvisoryCVE-2026-15534CVE-2026-19487

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online · 7d agoAI safety & security1

An Empirical Analysis of CodeQL False Positives and Query Refinements for Java Vulnerabilities

Study of 167 Java CVE instances finds CodeQL false positives follow recurring patterns; query refinements remove 81.8% of reviewed ones.

Researchers ran CodeQL's Java security query suite on 167 CVE instances from 110 projects, manually reviewing 500 sampled false-positive paths and building a five-category taxonomy led by Missed Path Constraint or Sanitization (36.6%), Benign Execution Context (29.4%), and Missing Trust Boundary Modeling (27.6%). Guided by the taxonomy, query-level refinements removed 81.8% of reviewed false positives and 15.8% of reported paths across the selected queries while retaining 7 of 8 true positives. To address generalization, agentic coding tools given the refinement patterns as templates adapted them to new projects successfully in 56% and 62% of tasks, versus 28% without guidance.

arXiv cs.CR · 12d agoResearch1

Safe Meta-Reinforcement Learning via Information Space Reachability

Safe meta-RL framework reasons about safety in information space, learning a safety value function used for safety filtering and constrained policy optimization.

The paper proposes safe meta-RL that reasons about safety in information space, capturing both physical state and the agent's belief over the underlying task. A safety value function measures the probability of avoiding unsafe regions indefinitely and satisfies a self-consistency condition and Bellman equation, making it learnable via meta-RL. The resulting algorithm uses the learned function for safety filtering and constrained policy optimization, with effectiveness demonstrated on meta-RL benchmarks.

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

WebPros security advisory (AV26-908)

Canada's Cyber Centre relays WebPros advisories for SQL injection (CVE-2026-67401) in cPanel and two ConfigServer Firewall flaws.

The Canadian Centre for Cyber Security published advisory AV26-908 covering vulnerabilities in WebPros products, including cPanel & WHM and ConfigServer Security & Firewall (CSF). Affected cPanel builds include versions prior to 11.110.0.143, 11.134.0.55, 11.136.0.39, 11.138.0.4 and WP2 11.138.1.9, while CSF versions 14.00-16.29 (CVE-2026-65638) and 2.15-16.29 (CVE-2026-65639) are also affected. CVE-2026-67401 describes SQL injection in cPanel's EmailTrack functionality. Users and administrators are encouraged to review the advisories and apply available updates.

Canadian Centre for Cyber Securityupdated · 5d agofirst · 5d agoAdvisory 3 sourcesCVE-2026-65638CVE-2026-65639CVE-2026-67401

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

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

Your Critical Vulnerabilities Might Not Be Your Biggest Risk

Autonomous penetration testing advocates prioritize exploitable attack paths over raw vulnerability severity for continuous security validation.

The article argues that scanner severity scores lack context: a critical flaw behind strong segmentation may be low priority, while a medium flaw on internet-facing systems can provide a foothold chained toward sensitive data. It positions autonomous penetration testing and attack path validation as the execution layer for continuous security validation, replacing point-in-time assessments. The piece is vendor-authored thought leadership rather than incident or vulnerability news.

The Hacker News · 5d agoIndustry1

Emacs arbitrary code execution: incomplete fix for CVE-2024-53920

Incomplete fix for Emacs CVE-2024-53920 allows arbitrary code execution when viewing or editing untrusted files in non-Lisp modes like Perl flymake.

Bas Alberts of GitHub Security Lab discovered that the patch for CVE-2024-53920, an arbitrary code execution flaw in Emacs, was incomplete. Code execution remains possible when viewing or editing untrusted text files in modes other than Emacs Lisp mode, for example Perl files with flymake mode enabled. All Emacs versions affected by the original CVE remain affected by the incomplete fix.

oss-security · 2d agoVulnerabilityCVE-2024-53920

CVE-2026-86219: Authen::SASL::Perl::DIGEST_MD5 versions before 2.2100 for Perl accept replayed authentication responses via unverified nonce in server_step

Authen::SASL::Perl::DIGEST_MD5 before 2.2100 for Perl accepts replayed DIGEST-MD5 authentication responses via unverified nonce handling (CVE-2026-86219).

CVE-2026-86219 affects Authen::SASL::Perl::DIGEST_MD5 versions before 2.2100 for Perl. The server_step function does not verify the nonce, allowing replayed authentication responses to be accepted in DIGEST-MD5 SASL exchanges. The fix is available in version 2.2100 of the perl-authen-sasl distribution.

oss-security · 9d agoVulnerabilityCVE-2026-862191

ZDI-26-616: Koha Eval Code Injection Remote Code Execution Vulnerability

ZDI disclosed CVE-2026-19780, a CVSS 8.8 authenticated eval code-injection flaw in Koha enabling remote code execution.

Zero Day Initiative advisory ZDI-26-616 describes a code injection vulnerability in the Eval component of Koha, the open-source integrated library system. A remote attacker must authenticate before injecting and executing arbitrary code on affected installations. ZDI assigned the flaw a CVSS 3.0 rating of 8.8.

ZDI Published Advisories · 8d agoVulnerabilityCVE-2026-197801

GNU security advisory (AV26-923)

Canadian Cyber Centre advisory AV26-923 flags a stack overflow in GNU libextractor before v1.15 via OLE2 files.

The Canadian Centre for Cyber Security issued advisory AV26-923 on September 15, 2026, covering CVE-2026-91752, a stack overflow vulnerability in GNU libextractor versions prior to 1.15 triggered via OLE2 file parsing. The Cyber Centre encourages users and administrators to review the provided links and apply necessary updates as they become available.

Canadian Centre for Cyber Security · 1d agoAdvisoryCVE-2026-91752

From 88 lines to 1: Detecting DLL hijacking with Elastic Defend

Elastic condenses 88 lines of detection logic into one Elastic Defend 9.5.0 rule catching the DLL hijacking used by a ClickFix campaign.

The ClickFix campaign side-loads a malicious mscoree.dll next to a signed Microsoft binary and also ships a driver to kill Elastic Endpoint. Elastic rebuilt the DLL as a NativeAOT library, dropped it beside the signed binary, and confirmed that Elastic Defend 9.5.0 flags the load. The post replaces 88 lines of detection logic with a single rule for DLL search-order hijacking.

Elastic Security Labs · 19d agoTools in the wild

Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?

A systematic study shows input-level adversarial defenses provide inconsistent, often near-zero protection against observation-level attacks on video LLMs.

Researchers introduce DefTEval, a controlled framework testing eleven input-level defenses against five attack types across five video LLMs. Harmful-content detection rates are frequently near zero, and defenses fail even when attacks embed harmful signals in every sampled frame. Token compression discards localized safety features and modality fusion down-weights weakened visual signals, with defense outcomes dominated by model architecture rather than the defense method.

arXiv cs.CR · 8d agoAI safety & security

SEMA-GUARD: Semantic and Graph-Based Vulnerability Detection in Assembly Code

SEMA-GUARD uses semantic analysis and graph neural networks to detect vulnerabilities in assembly code, achieving 85.1% accuracy on a Juliet-derived benchmark.

SEMA-GUARD is a framework that detects vulnerabilities in compiled programs when source code is unavailable, targeting malware, firmware, and embedded systems analysis. It enriches control flow graphs with low-level execution semantics including stack manipulations, memory accesses, and data flow. Evaluated on a Juliet Test Suite set compiled to assembly and split into function-level chunks, it achieves 85.1% accuracy and an F1 score of 0.801, outperforming purely statistical or structural approaches.

arXiv cs.CR · 1d agoResearch1

What researchers learned about building an LLM security workflow

Oslo and FFI researchers show structured agentic workflows lift LLM alert-triage accuracy from 0% to about 93% on malicious cases.

Researchers at the University of Oslo and the Norwegian Defence Research Establishment tested GPT-5-mini, Claude 3 Haiku, Qwen3:30B, and Gemma 3:27B on alerts from the AIT Log Data Set V1.1; given only alert descriptions and log summaries, all four models correctly flagged zero percent of true-positive cases involving reconnaissance, brute-force logins, and initial access. Wrapping the same models in a workflow with constrained SQL queries over Suricata logs, an evidence summarizer, and a verdict stage with revision loops raised malicious-case accuracy to an average of 93 percent, with GPT-5-mini identifying every malicious case across 100 runs. The authors flag it as a proof-of-concept on one synthetic scenario and note models skewed conservative on benign alerts, with GPT-5-mini marking every benign case uncertain.

Help Net Security · 23d agoAI research1

WebPros security advisory (AV26-861)

Canada's Cyber Centre relayed a cPanel advisory for CVE-2026-65643, a domain parking vulnerability fixed in multiple cPanel/WHM releases; admins should update.

Canada's Cyber Centre issued advisory AV26-861 relaying cPanel's disclosure of CVE-2026-65643, a vulnerability in cPanel's Domain Parking functionality. Affected cPanel & WebHost Manager (WHM) builds include all releases prior to 11.110.0.141, 11.134.0.53, 11.136.0.37, 11.138.0.2, and WP2 11.138.1.7. Administrators are urged to review vendor guidance and apply updates. No exploitation details were provided in the advisory.

Canadian Centre for Cyber Security · 19d agoAdvisoryCVE-2026-65643