Fake ChatGPT, Gemini, and Claude Ad Portals Capture Credentials and MFA Codes
Cybersecurity researchers have disclosed details of a "human-operated phishing platform" that impersonates advertising p
2026-10-07 归档
今日共收录 1979 条安全情报，包含 1214 个 CVE，387 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Google Pauses OSS Product Bug Bounty Rewards After Surge in Invalid Automated Reports
Google has stopped accepting product vulnerability reports through its bug bounty program for its open-source software.
Long-Running NPM Malware Campaign Accumulates 40,000 Downloads
Since August 2023, attackers have published eight malicious packages as part of the MALFEX supply chain campaign. The po
Secure Speculative Decoding for Large Language Models
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by
Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance withou
Case-Level Verification in Scanner-LLM Cascades: Overcoming the Alert Aggregation Bottleneck to Expand the FRR-TPR Trade-off Space
Dynamic Application Security Testing (DAST) scanners achieve high recall but also produce a large number of false positi
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depen
Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code
Large Language Models (LLMs) are widely used to generate code. Although their functional plausibility keeps improving, t
Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering
AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that
ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety--Utility Co-Enhancement
Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromi
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almo
Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial conte
SkillPoison: Progressive Skill Poisoning via Successful Experiences
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill a
HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?
Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain
Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain thr
Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security
Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicula
Weight Oracles: Reading Neural Network Weights with Language Models
Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specif
Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents
Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately
Efficient Auditing of Adversarial AI Agent Behavior from Agent Traces
AI agents powered by large language models (LLMs) can perform complex tasks but may harm the systems they operate in, ei