OpenAI GPT-6 Cyber uncovers 81 Firefox vulnerabilities
The model identified 81 high-severity Firefox flaws and developed exploits for 948 Linux kernel issues during internal testing.
1
Stories per day · 30 days
2 RSS
Relatedabstract-syntax-tree1binary-analysis1biomedical1control-flow-graph1c-source1cwe1defi1economic-manipulation1firefox1gpt-61jailbreak1linux-kernel1llm-agents1neural-decompilation1openai1primevul1prompt-injection1reva1
19 stories, newest first · one card per story
Stories tagged #vulnerability-detection
Economic-State Manipulation Vulnerabilities in DeFi
ESM study of 276 attacks reveals limited coverage by existing detectors.
REVA screens new functions for vulnerabilities in about one second
On PrimeVul, REVA with GLM-5.3-Flash matches VulTriage accuracy while running over 250 times faster.
Code-view ensemble lifts LLM vulnerability detection to 78% F1
Source, AST, and CFG models are complementary; logical rules plus majority voting beat the best single view by 5 F1 points.
VulDec pairs neural decompilation with binary vulnerability detection
Tuned LLM detectors reach macro F1 0.61 on a realistic test set with a 3% vulnerability rate.
One-sentence attack steers LLM agents to wrong beliefs
Best-of-10 attacks overturned correct answers at 54.9% proprietary and 80.0% open-weight mean rates.
OpenAI Launches Codex Security Cloud for Always-On Application Security Scanning
OpenAI launched Codex Security Cloud, an always-on AppSec service that scans GitHub repos, validates findings, and drafts remediation patches for human review.
DARPA Selects Xint to Use AI in Securing Military Messaging Apps
DARPA selected AIxCC winner Xint to autonomously analyze and patch vulnerabilities in Department of War messaging apps like Signal.
A Function-level Dataset of Vulnerable and Fixed Source Code in JavaScript and TypeScript
JsVul pairs vulnerable and fixed JavaScript and TypeScript functions from seven sources.
Detecting Logic Vulnerabilities Across the Contract and Device Layers of Blockchain-Enabled IoT With Multi-Agent Heterogeneous Graph Attention
MA-HGAT framework detects logic vulnerabilities across smart contract and IoT device firmware layers using multi-agent heterogeneous graph attention.
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.
AWS puts AI vulnerability detection to the test, and false positives pile up
AWS publicly released its Deception Benchmark (14,822 samples) showing leading AI models falsely flag 41-99% of safe code as vulnerable.
3
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.
Towards Scalable and Cost-Efficient Vulnerability Detection: A Study on Automatic Query Generation
A study finds LLM-synthesized CodeQL queries improve average F1-score by 82% over baseline queries, offering scalable vulnerability detection versus direct LLM scanning.
When LLM Decompilers Recompile More and Preserve Less
Researchers show LLM decompiler outputs can recompile yet diverge behaviorally, proposing the Decompile-Diverge fuzzing oracle to catch hidden changes.
The History Is the Detector: Executing CVE Patch History, End-to-End
BUGSTONE-E2E converts CVE patch history into executable LLM-guided detection rules, yielding 1,033 rules and 644 runtime-verified findings across 14 programs.
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.
Introducing Gemini 3.8 Flash and 3.8 Flash Cyber
Google DeepMind releases Gemini 3.8 Flash and 3.8 Flash Cyber with improved reasoning, coding, and cybersecurity vulnerability detection and automated patching.
3
Can your coding style predict whether your code is vulnerable?
University of Massachusetts Dartmouth researchers present VulStyle, a stylometry-based vulnerability detector that also exposes benchmark reliability problems.
2