💉 Prompt Injection - hop1.ng.1357 · Scour

PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free 🛡️AI Security

injecguard.github.io·6d·Hacker News

The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail? 🛡️AI Security

arxiv.org·1d

Show HN: Prompt injection detector beats ProtectAI by 19% accuracy, 8.9x smaller 🛡️AI Security

huggingface.co·1d·Hacker News

ShieldStack TS – LLM security middleware for TypeScript 🪝eBPF

github.com·5d·Hacker News

Show HN: BrokenClaw Part 5: GPT-5.4 Edition (Prompt Injection) 🕳LLM Vulnerabilities

veganmosfet.codeberg.page·2d·Hacker News

Ask HN: What's the state of multimodal prompt injection defence in 2026? 🕳LLM Vulnerabilities

news.ycombinator.com·1d·Hacker News

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems 🔧Agent Tooling

arxiv.org·3d

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills 🛡️AI Security

arxiv.org·1d

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment 🛡️AI Safety

arxiv.org·2d

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation 📚RAG

arxiv.org·4d

Understanding the Effects of Safety Unalignment on Large Language Models 🛡️AI Safety

arxiv.org·4d

Loading more...