Krebs identifies a St. Petersburg man as Qilin ransomware admin
Leaked records and forum pivots name 36-year-old Aleksey Yakovtsev; Qilin claims 365 victims in three months.
Stories per day · 30 days
4 RSS
Relatedwatermarking3iran2irgc2llm-agents2agent-security1ai-coding1autonomous-cyber-weapons1claude1computer-vision1copyright1danfoss1double-extortion1explainability1fingerprinting1france1gumbel-max1hacker-news1ics1
22 stories, newest first · one card per story
Stories tagged #attribution
France blames IRGC unit for October supermarket fridge hacks
A joint report names IRGC unit Shahid Kaveh; attacks hit about 700 stores on October 11-12, and US sources reportedly had only low-confidence attribution.
France blames IRGC units for refrigeration attacks on 700 supermarkets
CERT-FR linked the October 11–12 sabotage to Shahid Kaveh; Paris opened a probe and will seek EU sanctions.
SkillCODER fingerprints LLM agent skills for copyright and buyer attribution
Across three domains, six models and three frameworks, owner verification reached 99.2% and buyer Top-1 attribution 99.3%.
AgentAnchor watermarks LLM agent logs against cross-session forgery
A trusted verifier checks a disputed trajectory without rerunning the agent, using wrong-key calibration and abstention.
Paper proposes 72-hour legislative notice for autonomous cyber weapons
Authors conclude at most one of six oversight bodies could lawfully receive that notice today.
BLADE improves multi-mode attribution of LLM watermarks
On OPT-1.3B and other open-weight models, BLADE beat compared detectors across modes and substitutions.
Spectral-Spatial Interpretation attributes images by position and channel
On HLS Burn Scar, SSI beat an MC-Owen estimator while using about 6% of its evaluation budget.
U.S. Offers Up to $10 Million for Tips on Zhang Yu, Charged in HAFNIUM Hacks
US State Department offers up to $10 million for tips locating Zhang Yu, Chinese national charged in HAFNIUM Microsoft Exchange hacks.
7
Stop My Dancing! Understanding, Detecting and Attributing Motion-Aware Deepfake Videos
MoDA detects and attributes motion-aware deepfake videos, reaching 94.8% in-distribution accuracy on a new benchmark.
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
GROB uses public Internet traces to investigate possible autonomous-agent activity without privileged telemetry.
Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses
LipDA detects and attributes LipSync forgeries from mismatches between lip motion and head pose.
LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization
LiBRA attack removes AI-image watermarks in an autoencoder's latent space while preserving quality, steering decoder confidence toward random guessing instead of inversion.
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
LRP-radial-all explains hyperbolic networks with attributions consistent across equivalent geometric implementations.
Sybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and Autonomous Vehicles Using Dynamic Semi-supervised GNN
Sybil-TraceGuard, a dynamic semi-supervised spatio-temporal GNN, links fragmented Sybil pseudonyms in connected vehicles back to their source attackers.
Google stole open source code without crediting the authors (Artemis/Minitap)
Minitap alleges Google's Artemis mobile-agent project reused its open-source mobile-use code and stripped author attribution, despite Apache 2.0 requirements.
8
OpenAI’s feud with mathematicians is only escalating
25 Fields Medalists sign an open letter warning AI labs threaten math attribution; NYU's Tristan Buckmaster accuses OpenAI of pressuring him over collaborator credit.
1
What OpenAI’s latest controversy tells us about the future of math
OpenAI says its agents solved the Navier–Stokes Millennium Problem using an internal model, amid uncredited-work accusations from mathematicians Buckmaster and Alpöge.
North Korea’s Lazarus Operates Through Six Distinct Cyber Clusters
Sekoia and Kudelski Security reclassify North Korea's Lazarus umbrella into six clusters spanning espionage, financial theft, and fake IT worker operations.
3
Edge infrastructure under siege: what two independent datasets reveal about who's exploiting your perimeter
Joint Tenable-SentinelOne analysis of 93 CVE-actor attribution pairs shows nation-state and criminal groups independently converge on the same edge infrastructure.
1
Introducing Unit 42’s Attribution Framework
Unit 42 releases its Attribution Framework, a systematic method using Diamond Model and Admiralty scores to attribute activity clusters to named threat actors.
4
Researchers Link 'Jewelbug' Chinese APT to Hack-for-Hire Operations
Broadcom researchers link the Chinese APT group 'Jewelbug' to a lucrative crypto-fraud hack-for-hire operation.