First reported arxiv.org
Research · latest
First reported openreview.net
Defending FCG-based Malware Detectors Against Metamorphic Android Variants via LLM-Powered Code Refactoring
A research paper (ACL ARR 2026 submission) introduces FCGA, a framework that uses LLMs to synthesize code augmentations for training function-call-graph-based Android malware classifiers, hardening them against LLM-rewritten metamorphic malware variants. The authors report that graph-based detectors enriched with LLM features drop over 60% in accuracy against LLM-rewrite attacks, and FCGA improves robustness by up to 8% over baselines. Details →First reported arxiv.org
ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments
ALIBI is an automated adaptive black-box attack framework that evades LLM-based vulnerability detectors by inserting adversarial source-code comments that steer detector reasoning or fabricate external tool results without changing program behavior. Evaluated against four detectors including frontier multi-agent systems, it achieves attack success rates exceeding 90% across 125 real-world null-pointer dereference vulnerabilities, reaching 100% on one system, while prompt-level defenses offer limited robustness. Details →How the wire is made
Poll & cluster
Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.
Curate
AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.
Every item here is one machine-curated intelligence object, not a headline.
Read the wire for free. There is a small charge to ask the index questions.
The wire, open
The complete curated feed, no key required.
- GET /feed.xml — RSS 2.0, every item
- GET /api/items — read-only
The vector desk
Query the index by meaning, not just keyword.
- GET /api/items?tags=&minSeverity=&itemType=
- GET /api/search?q= — keyword
- GET /api/semantic?q= — vector