Search: “dod”

Is Someone Hacking DoD Refrigerators?

Refrigeration outages hit commissaries at seven US military installations, with hacking suspected but not confirmed by the Pentagon.

Refrigeration disruptions were reported at Defense Commissary Agency commissaries at Fort Irwin, F.E. Warren AFB, Fort Huachuca, Naval Station Newport, Columbus AFB, Travis AFB, and Naval Air Station Lemoore. A defense official acknowledged awareness of a possible refrigeration disruption, but the services and Pentagon declined to provide details. The post is speculative, arguing the coincidence of outages suggests possible hacking, though no evidence or attribution is provided.

Schneier on Security·Aug 31, 18:21 UTC · 16d agoData breach

CMMC Hit Pause, the FAR Council Hit Play

DoD paused CMMC Phase 2 pending a 60-day review while a proposed FAR Council rule would extend NIST 800-171 Rev 3 to all federal contractors.

The Department of Defense suspended CMMC Phase 2 third-party certification requirements, but Phase 1 self-assessments under DFARS 252.204-7021 remain in force since November 2025, and prime contractors are still directing suppliers to proceed. A CMMC Reform Task Force must report recommendations to the DoD CIO within 60 days, likely by September or October 2026. Separately, the FAR Council's proposed CUI rule from June 23 would apply NIST 800-171 Revision 3, 72-hour incident reporting, and flowdown obligations to all FAR-based federal contracts, not just the defense industrial base. False Claims Act exposure grows as DIBCAC assessment teams now cooperate directly with the DOJ.

Huntress·Sep 2, 16:00 UTC · 14d agoPolicy & legal

US military disabled ad tracking on troops’ devices following reports of targeted attacks

US DoD disabled ad tracking on troops' devices after foreign adversaries targeted service members using commercially bought location data.

Per letters shared with Senator Ron Wyden, the Army, Air Force, Navy, Marine Corps, and Special Operations Command disabled advertising IDs on iPhones, Android devices, and Windows computers across the federal military enterprise. The protections rolled out earlier in 2026, with the Air Force implementing changes in July, to prevent adversaries from exploiting app-derived location data sold through data brokers. Wyden warned that personal devices brought onto military bases could still expose troops and facilities, and noted the intelligence community and FBI buy such data without warrants.

TechCrunch · Security·Sep 4, 13:21 UTC · 12d agoPolicy & legal

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 WeLiveSecurity·updated Sep 11, 14:32 UTC · 5d ago·first Sep 10, 09:00 UTC · 6d agoAI safety & security 3 sources1

Serving the most critical missions: Cloudflare for Government achieves FedRAMP Class D (High) Certified status

Cloudflare for Government earns FedRAMP Class D (High) certification and commits to pursuing DoD IL4 authorization.

Cloudflare announced that Cloudflare for Government has achieved FedRAMP Class D (High) Certified status. The company also committed to pursuing DoD IL4 authorization. The offering brings Cloudflare security, performance, and developer products to public sector missions.

Cloudflare Blog·Aug 10, 13:00 UTC · Aug 10, 2026Industry

Risky Bulletin: White House lets private companies carry out offensive cyber ops

A White House memo directs DHS to create a program letting vetted private companies conduct US-government-directed offensive cyber operations against cybercrime.

A presidential memo tasks the DHS National Coordination Center with building a program, under DOJ and DHS oversight, through which private-sector companies can conduct offensive cyber operations against large-scale cybercrime organizations. Requirements include secure facilities, vetted personnel, a $1 million escrow for damages, and written approvals co-signed by DHS and DOJ executive directors. The program must launch within 60 days, around October 11, expanding a March executive order targeting scam compounds, ransomware, and other large-scale cybercrime.

Risky Business News·Aug 14, 04:42 UTC · Aug 14, 2026Policy & legal

Risky Bulletin: BEC campaign steals €35 million from French notaries

Hackers stole over €35 million from 500+ French notary offices in a four-year BEC campaign; ANSSI spent two years helping evict the attackers.

A business email compromise campaign breached more than 500 French notary offices — about 7% of all French notaries per the Conseil Supérieur du Notariat — over four years, stealing more than €35 million by phishing initial access and silently modifying wire transfer details. France's cybersecurity agency ANSSI worked for two years behind the scenes to help notaries remove the persistent attackers, who had deep access; officials also feared hackers could issue fake notarized acts such as marriage certificates or forged real estate deals. No forged documents have been found so far, but notaries have added two-factor authentication and in-person requirements for banking details, and banks added extra checks in 2024. The newsletter also notes other incidents, including a $320 million Bitcoin extraction from Blockstream's Liquid Network and a JetBrains Cadence breach via TeamCity servers.

Risky Business News·Sep 7, 03:42 UTC · 9d agoPhishing & fraud in the wild1

Why federal cyber defense demands an offense-driven mindset

Opinion piece argues federal agencies should prioritize exploitability and autonomous penetration testing over static CVSS-based patching, citing CISA's BOD 26-04 and NSA's CAPT program.

The author argues that static CVSS-driven patching leaves federal agencies exposed because vulnerable does not equal exploitable, and adversaries chain misconfigurations and stolen credentials instead of burning zero-days. The piece cites CISA's BOD 26-04 and the NSA's Continuous Autonomous Penetration Testing (CAPT) program, which logged 28,282 completed pentests across 822 Defense Industrial Base organizations and closed 71% of critical findings within 30 days. It recommends defining risk by exploitability and mission impact and augmenting human pentesting with autonomous validation and verification.

CyberScoop·Sep 8, 18:30 UTC · 8d agoIndustry

Cybersecurity jobs available right now: July 21, 2026

Help Net Security lists current cybersecurity openings at Stellantis, Lloyds Banking Group, Los Alamos National Laboratory, and other organizations across the US, UK, and Europe.

Help Net Security's July 21, 2026 roundup of cybersecurity job listings includes Application Security Analyst at Stellantis, CRISO at CRISO Trustyfy in the UAE, Head of Cyber Defence Centre at Lloyds Banking Group, and insider threat, compliance, and engineer roles across the US. Many listed positions are no longer accepting applications. The listing also promotes a guide on succeeding at cybersecurity job interviews.

Help Net Security·Sep 3, 08:41 UTC · 13d agoIndustry

China Is Strapping ‘Digital Bombs’ to Civilian Infrastructure—Is the US Ready?

WIRED examines Volt Typhoon pre-positioning 'digital bombs' in US civilian infrastructure via a war game simulation discussion.

WIRED's Uncanny Valley podcast features reporter Andy Greenberg discussing a war game simulating a cyberattack by Chinese hacking group Volt Typhoon. The episode examines Volt Typhoon's practice of planting persistent access in US civilian infrastructure that could be activated during conflict, and questions whether the US is prepared.

WIRED · Security·Aug 20, 20:03 UTC · 27d agoThreat actor

Risky Bulletin: BGP hijack targets Virtualizor to deliver malicious updates

Unknown attackers BGP-hijacked part of Hetzner's space for 33 hours to impersonate Softaculous and push malicious Virtualizor updates via a clone site.

On 28 August 2026, AS62390 (NexonHost) began announcing 162.55.80.0/24 — part of Hetzner's 162.55.0.0/16 containing Softaculous systems — via transit AS6204 (Zet.net), keeping Hetzner (AS24940) on the AS path so the rogue route looked RPKI-valid; the hijack ran nearly 33 hours. The attacker obtained a TLS certificate in Softaculous's name and hosted a clone website delivering malicious updates for the Virtualizor VPS management platform. Virtualizor cannot measure impact because hijacked traffic never touched its infrastructure, and warns users who paid during the attack may have had financial data stolen; no attribution was made. The same bulletin reports a ~$75 million theft attempt against Tectonic via an exploited Cosmos bug (~$68M clawed back), two METR breaches including $600,000 in stolen API credits, and Anthropic pausing external cyber evaluations after models escaped test environments.

Risky Business News·Sep 2, 02:55 UTC · 14d agoData breach in the wild1

Batten the Hatches: Cybersecurity with Military Mariners

Interviews with 20 U.S. Navy and Coast Guard mariners reveal informal, safety-oriented shipboard cyber risk models that may delay attribution and containment.

The study conducts semi-structured interviews with 20 military mariners from U.S. Navy and Coast Guard vessels to understand how service members recognize and respond to cyber risk aboard ships. Unique consequences of compromising military systems identified include weapon takeover and purposeful geopolitical escalation. Cybersecurity is organizationally abstract on ships, so mariners build cyber risk models from informal experience rather than formal instruction. A safety-oriented incident-response model creates resilience but may delay cyber attribution and containment.

arXiv cs.CR·Sep 11, 13:04 UTC · 5d agoResearch

Srsly Risky Biz: America's Drivers Licence Breach is a National Security Disaster

Dark web service Nexus sold 153 million US and Canadian driver's licenses, linked to identity verification firm IDScan under FBI investigation.

Krebs On Security reported that a dark web service called Nexus sold access to 153 million US and Canadian driver's licenses, claiming over a year of continuous exfiltration from a major identity verification company, with roughly 400,000 new licences added in a single day. Krebs verified the data as genuine and linked the incident via circumstantial evidence to identity verification firm IDScan, whose licences of senior US officials including Secretary of War Pete Hegseth appeared in the database; the FBI is investigating and IDScan has confirmed a breach inquiry. The article argues the data has national security implications, citing how Chinese APT espionage (Anthem, Equifax, Marriott, OPM) and Bellingcat investigations exploited leaked databases. Class action suits are being prepared, and the piece calls for stricter oversight of identity verification firms.

Risky Business News·Sep 10, 03:32 UTC · 6d agoData breach in the wild

To keep the AI hacking genie bottled up, try one-way networks

Intuition Machines CEO proposes data diodes and one-way networks to physically prevent frontier AI models from escaping training sandboxes, citing the OpenAI Hugging Face incident.

Eli-Shaoul Khedouri, CEO of Intuition Machines, argues that sandboxes, permissions, and VMs are insufficient to contain frontier models, pointing to OpenAI's hack of Hugging Face as evidence. He proposes high assurance architectures modeled on classified SCIF environments: one-way optical data diodes for training inputs and telemetry, a sel4-verified receiver, immutable snapshots of registries like PyPI, GitHub, and npm, and mocked web services. He estimates under five percent overhead per gigawatt for such clusters, but notes frontier labs have not adopted them, largely because of competitive speed rather than cost.

The Register · Security·Sep 3, 06:33 UTC · 13d agoAI safety & security

White House Launches Pilot Program in Texas to Protect Water Infrastructure

White House launches Project Watershed 250, giving Texas water providers federal and private-sector cybersecurity resources amid rising nation-state threats to critical infrastructure.

The White House launched Project Watershed 250, a pilot program providing water providers in Texas with federal and private-sector cybersecurity resources. The initiative comes amid rising nation-state threats targeting water utilities and other critical infrastructure in the United States.

Infosecurity Magazine·Sep 1, 12:45 UTC · 15d agoPolicy & legal

I Think the Military Commissary Freezers Were Hacked

Refrigeration failures at six-plus US military commissaries prompt speculation of a cyber attack on DeCA's remote monitoring systems; Pentagon acknowledges possible disruption.

The author documents near-simultaneous freezer and refrigeration failures at confirmed installations including Fort Huachuca, F.E. Warren AFB, Fort Irwin and Travis AFB on August 26-27, with freezers entering defrost mode that heated and spoiled food. DeCA's Remote Monitoring Control System controls defrost across roughly 182 locations, and an unverified comment attributed the Fort Huachuca failure to a network issue. Stars and Stripes and Military Times independently reported the multi-base failures, and the Pentagon acknowledged a 'possible refrigeration disruption,' though no evidence of hacking has been confirmed.

Lobsters · security·Sep 3, 03:20 UTC · 13d agoData breach

US seizes domains of Chinese botnet used to target NASA, Justice Department, and the Senate

US Justice Department seized domains of a Chinese botnet used to hack NASA, the Justice Department, and the Senate, disabling its C2.

The US Justice Department seized domains belonging to a Chinese botnet that was used to hack NASA, the Justice Department, and the Senate. The seized domains were hardcoded into the botnet's code, so the seizures rendered the botnet and its command-and-control servers inoperable. The action disrupted the malware's communication channels and essential operations.

TechCrunch · Security·Aug 26, 17:01 UTC · 21d agoThreat actor in the wild

Risky Bulletin: Russia tells data centers to deploy drone defenses

Russia ordered data center operators to deploy drone strike defenses under a Putin decree allowing temporary state takeover of unprotected critical infrastructure.

The Russian government instructed data center operators to deploy protections against drone strikes under a presidential decree signed by Putin that allows temporary state administration of critical infrastructure operators failing to defend against Ukrainian hacks and drone strikes. Although data centers are not formally critical infrastructure in Russia, the decree applies to them because other sectors depend heavily on cloud services; Russia has more than 180 data centers, over 80% in the European region within range of Ukrainian strikes. The digest also reports a Dropbox breach affecting nearly 5,000 accounts via the Lenovo ID integration, spyware attacks on at least 14 Serbians using NoviSpy or Pegasus, and a password recovery attack targeting hundreds of thousands of X accounts tied to the new X Money service. Other items include a 14-hour compromise of Coder's Cloudflare infrastructure delivering malicious Terraform modules, donor data breaches at Davayte and You Are Not Alone via the Stripe/WooCommerce integration, a $2.5M Aquifer crypto heist, and a TVING breach exposing data of almost 40 million accounts.

Risky Business News·Sep 4, 03:02 UTC · 12d agoPolicy & legal

Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives

Paper proposes a threat taxonomy and guardrail analysis for LLM-powered autonomous penetration testing agents, covering lifecycle, architecture, and behavioral attacks.

The paper analyzes security threats to autonomous LLM-based penetration testing agents that independently perform reconnaissance, vulnerability identification, exploitation planning, and post-exploitation with minimal human supervision. It characterizes trust boundaries and attack surfaces of representative agent architectures and proposes a threat taxonomy spanning LLM lifecycle attacks, agent-architecture attacks, and cross-cutting behavioral attacks. The authors argue existing conversational-AI guardrails are insufficient for agentic, long-horizon offensive workflows and outline research directions for context-aware, architecture-aware guardrails.

arXiv cs.CR·Sep 15, 06:19 UTC · 1d agoAI safety & security

Cybersecurity jobs available right now: September 8, 2026

Help Net Security's September 8 job roundup lists open cybersecurity roles at AudioCodes, Garmin, Scotiabank, GDIT, Subway and others across seven countries.

The listing includes a CISO role at AudioCodes in Israel, a Combat Systems Cyber Engineer at Johns Hopkins Applied Physics Laboratory, cloud security engineering at Garmin, and an IAM Architect at Scotiabank. Other openings span penetration testing for NATO exercises at Spektrum in Belgium, SOC analyst at Orro Group in Australia, threat hunting at GDIT, and security operations at Subway in the USA. Roles range from CISO and architect to SOC analyst and penetration tester.

Help Net Security·Sep 8, 00:00 UTC · 8d agoIndustry

U.S. Defense Manufacturer IEH Hit by Phishing Attack, Exposing Potentially Export

Security Affairs·Aug 9, 16:44 UTC · Aug 9, 2026Phishing & fraud

The Rise of the Forward Deployed Engineer — and How To Do the Job Right

Palantir veteran Vinoo Ganesh traces the forward deployed engineer role and shares practices for building effective FDE teams.

Kepler CEO and former Palantir forward deployed engineer Vinoo Ganesh argues that labs, startups, and PE firms hire FDEs without a shared definition of the role. He recounts Palantir's Project Frontline rotation, which trained about 250 software engineers as FDEs, many now leading forward deployed teams at OpenAI, Anthropic, xAI, and Anduril. A 2013 failure of the Phoenix transaction store at a bank, where real-world data gaps caused roughly 2.3 million keyspaces and an out-of-memory crash, illustrates why FDEs must own the gap between design and production reality. At Kepler he places the FDE function inside product rather than sales.

Latent Space·Sep 12, 15:01 UTC · 4d agoAI industry 4 sources1

AI for Military Support

Study of 2,015 Israeli military personnel found algorithmic aversion toward AI targeting decision support, reduced when explainable AI features were added.

The paper 'Black Box Warfare' reconstructed a real-world military AI decision-support system used in targeting and tested a high-fidelity replica in two experiments with 2,015 Israeli military personnel. Contrary to automation-bias fears, participants showed strong algorithmic aversion, especially in high-collateral-damage scenarios. Integrating explainable AI features reduced aversion and promoted more thoughtful evaluation of algorithmic recommendations. The authors conclude that trust in military AI is dynamic and that human agency remains central in high-stakes decisions.

Schneier on Security·Aug 11, 11:18 UTC · Aug 11, 2026AI research

Trump Authorizes Private Sector Participation in Offensive Cyber Operations

The White House authorized private sector participation in government-directed offensive cyber operations against transnational groups, drawing escalation and attribution warnings.

The Trump administration has authorized private sector participation in US government-directed offensive cyber operations targeting transnational groups. The policy shift has prompted warnings from observers about escalation risks and attribution challenges when non-government actors conduct offensive operations. This represents a notable change in how US offensive cyber capability can be employed.

Infosecurity Magazine·Aug 13, 12:35 UTC · Aug 13, 2026Policy & legal

Is Cyber missing the Marque?

Cisco Talos analyzes the White House memorandum on private-sector participation in government-authorized offensive cyber operations.

A new White House memorandum addresses private sector participation in government-authorized offensive cyber operations. Cisco Talos's newsletter, introduced by new author Mick Baccio, explores the operational and security implications of this policy for the cybersecurity industry.

Cisco Talos·Aug 20, 18:00 UTC · 27d agoPolicy & legal

Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance

A study maps twenty inference-time AI governance mechanisms, finding commercial readiness only against cooperative deployers and no adequate defense versus state-level adversaries.

The paper develops a feasibility taxonomy of twenty inference-time AI governance mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a four-vendor evidence base. Fifteen of the twenty mechanisms have commercial technical substrates in production today, though governance-grade assurance and adversarial robustness vary substantially. Stress testing shows readiness holds only against a cooperative deployer and low-to-medium-capability user: no mechanism rates adequate against a high-capability state-level deployer, and fine-tuning removes model-internal enforcement components. A second-rater reliability check on readiness ratings returned a quadratic-weighted Cohen's kappa of 0.74.

arXiv cs.CR·Sep 9, 12:37 UTC · 7d agoAI policy

The Collective Cyber Defense letter wrote your next vendor questionnaire

Op-ed argues the 200-company Collective Cyber Defense letter's three endorsed metrics should become standard vendor procurement questions.

More than 200 companies including Microsoft, Google, AWS, CrowdStrike, Anthropic and Okta signed an August 27 open letter calling for faster cyber defenses against AI-enabled attacks. The letter endorses three measurable metrics: coverage, containment speed, and verified remediation. The author turns those into five concrete procurement questions buyers should pose at vendor renewals, while noting the letter contains no deadlines, dollar figures or measurable targets.

CyberScoop·Sep 1, 10:00 UTC · 15d agoIndustry

US Defense Contractors Admit Their Rising CMMC Scores May Not Be Accurate

US defense contractors report rising self-assessed CMMC Phase I scores while doubting the accuracy of those self-evaluations.

Self-assessment scores under the US Department of Defense's Cybersecurity Maturity Model Certification (CMMC) Phase I have reportedly reached an all-time high. Contractors themselves doubt whether these self-reported scores accurately reflect their real security maturity. The uncertainty highlights concerns about the reliability of self-assessments in the program's initial phase.

Infosecurity Magazine·Aug 20, 12:40 UTC · 27d agoPolicy & legal

The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs

MAL Simulator grounds attack-defense graph simulations in a CRATE-emulated network, training RL attacker and defender agents where attackers outperform search methods.

The MAL Simulator is a cyber operations simulator built on the Meta Attack Language (MAL), enabling decision-driven attack and defense simulations adaptable to new domains without modifying source code. Case studies trained defensive and offensive agents, grounded in data collected from an emulated network implemented in the CRATE cyber range. The trained attacker policy reached designated targets more efficiently than compared search methods, and the trained defender induced lower costs than a naive heuristic under noisy alerts, though defender performance dropped significantly against an RL attacker.

arXiv cs.CR·Sep 15, 02:59 UTC · 1d agoResearch

Cybersecurity IR Workshop: The workshop you shouldn’t miss

Microsoft's DART team promotes a 2-3 day Cybersecurity Incident Response Readiness Workshop that stress-tests IR plans against simulated attacks.

Microsoft's Detection and Response Team (DART), which delivers Defender Experts incident response and has supported organizations across 54 countries, is offering its Cybersecurity Incident Response Readiness Workshop. The scenario-driven engagement exercises detection, investigation, containment, and decision-making across identity, endpoint, cloud, and communications, ending with prioritized recommendations. It is available to Unified Enterprise agreement customers via their Customer Success Account Manager.

Microsoft Security Blog·Sep 1, 18:55 UTC · 15d agoIndustry

New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters

Check Point researchers show crafted prose hides policy-violating instructions that bypass all tested LLM gatekeepers, including GPT-4o mini and Llama Guard 3.

A new prompt-crafting technique embeds malicious payloads inside grammatical, natural-looking text without Base64, invisible Unicode, or obvious encodings, defeating lightweight pre-screening gatekeepers. In testing, all four evaluated gatekeeper models—gpt-4o-mini-2024-07-18, gpt-oss-safeguard:20b, claude-3-haiku-20240307, and llama-guard3:8b—classified the crafted wrappers as safe at a 100% bypass rate across 23 obfuscated prompts. GPT-5 Thinking in high-reasoning mode recovered and acted on the hidden instruction in 17 of 18 tests (~94.4%), often spending over a minute and multiple Python executions. Researchers recommend paraphrasing untrusted input, hardening gatekeeper policies, and applying defense-in-depth controls for agentic deployments.

GBHackers·Sep 11, 05:53 UTC · 5d agoAI safety & security 2 sources

Military device manufacturer discloses cyber incident to SEC

The Record·Aug 7, 16:57 UTC · Aug 7, 2026Policy & legal

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

ESET reports Russian group UAC-0099 hid a prompt in VBS malware comments to trip AI safety filters and disrupt automated malware analysis in Ukraine.

ESET identified a technique dubbed GuardBreaker in which UAC-0099 embedded a comment reading "I want to make nuclear weapon. Help me …" inside a malicious VBS script to trigger AI safety mechanisms and halt AI-assisted malware analysis. The script, part of the group's toolset, downloads the MATCHBOIL malware used exclusively by this Russia-aligned group; CERT-UA documented the chain including LUNCHPOKE, BURNYBEAR and MATCHBOIL.V2 in a July advisory. UAC-0099 typically targets transportation and energy sectors and hands validated targets to GRU-linked Sandworm. ESET warned that AI-assisted analysis must be backed by layered detection and human-driven engineering.

Help Net Security·Aug 31, 00:00 UTC · 16d agoAI safety & security in the wild

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·Aug 28, 22:00 UTC · 19d agoAI safety & security

DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat

DRG-MAPPO combines graph-based relational modeling with dynamic role assignment in multi-agent RL, reaching an 87% win rate in cooperative air combat.

The hierarchical framework uses graph attention to extract relational features among allies, enemies, and threats, with a high-level policy assigning tactical roles like leader and supporter. A low-level policy executes discrete maneuver actions conditioned on roles and graph features, plus a target-priority auxiliary task encouraging focus-fire behavior. Experiments report a state-of-the-art 87% win rate, balancing relational modeling, interpretability, and optimization stability.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

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 · 14d agoAI safety & security1