Black-Box Adversarial Patch Attacks on VLAs via Ancestor VLM Exploitation
Vision-Language-Action models (VLAs) are increasingly deployed in safety-critical physical environments, yet their adver
2026-10-09 归档
今日共收录 747 条安全情报，包含 0 个 CVE，359 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain
When AI Finds Hidden Messages, Does It Report?
When an assistant encounters a message for another AI, does it tell its user? Four fixed model-provider deployments perf
Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
DP-SGD protects training data by adding Gaussian noise to clipped gradients. The amount of noise is usually chosen by ru
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certif
Beyond FAIR: A Fitness Function Framework for Sustainable Research Software
Research software sustainability is often assessed through the FAIR principles: findability, accessibility, interoperabi
PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners
Agent skills combine instructions with executable resources, giving third-party packages access to an agent's runtime. E
Constitution-Guided Watermarking
Watermarking enables language model providers to identify text generated by their models. However, its desired propertie
Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents
Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observ
Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate mod
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, s
Cost of Delay for Post-Quantum Migration: Putting Classical and Harvest-Now-Decrypt-Later Risk on One Ordered List
Organisations deciding which assets to migrate to post-quantum cryptography first, and how that work competes with a bac
Visual Memory Attacks Can Persist Through The KV Cache
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images.
抢先加入AI时代顶尖安全团队！阿里云2027届实习生招聘来了！
抢先加入AI时代顶尖安全团队！阿里云2027届实习生招聘来了！
决赛直播｜第四届阿里CTF安全挑战赛
决赛直播｜第四届阿里CTF安全挑战赛
Control CenterManage your security and delivery services
Control CenterManage your security and delivery services
See all Cybersecurity
See all Cybersecurity
Our Infrastructure
Our Infrastructure
OpenClaw安全使用实践指南
OpenClaw安全使用实践指南
关于OpenClaw安全应用的风险提示
关于OpenClaw安全应用的风险提示