#attack-vectors News & Analysis

5 articles tagged with #attack-vectors. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

AIBearisharXiv – CS AI · Apr 77/10

🧠

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

Researchers conducted the first real-world safety evaluation of OpenClaw, a widely deployed AI agent with extensive system access, revealing significant security vulnerabilities. The study found that poisoning any single dimension of the agent's state increases attack success rates from 24.6% to 64-74%, with even the strongest defenses still vulnerable to 63.8% of attacks.

🧠 GPT-5🧠 Claude🧠 Sonnet

AIBearisharXiv – CS AI · Mar 267/10

🧠

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Researchers have discovered a new black-box attack method called Tree structured Injection for Payloads (TIP) that can compromise AI agents using Model Context Protocol with over 95% success rate. The attack exploits vulnerabilities in how large language models interact with external tools, bypassing existing defenses and requiring significantly fewer queries than previous methods.

AINeutralarXiv – CS AI · Mar 57/10

🧠

Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

Researchers propose a new goal-driven risk assessment framework for LLM-powered systems, specifically targeting healthcare applications. The approach uses attack trees to identify detailed threat vectors combining adversarial AI attacks with conventional cyber threats, addressing security gaps in LLM system design.

AIBearisharXiv – CS AI · Mar 166/10

🧠

Prompt Injection as Role Confusion

Researchers have identified 'role confusion' as the fundamental mechanism behind prompt injection attacks on language models, where models assign authority based on how text is written rather than its source. The study achieved 60-61% attack success rates across multiple models and found that internal role confusion strongly predicts attack success before generation begins.

CryptoBearishRekt News · Jun 96/106

⛓️

Social Recovery Wallets are Broken by Design

The article argues that social recovery wallets fundamentally undermine cryptocurrency's trustless design by introducing human guardians as potential points of failure. It suggests that while marketed as user-friendly security solutions, these systems actually create new attack vectors by reintroducing human trust dependencies.