Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Safety in Embodied AI: Risks, Attacks, and Defenses

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System

Attention Tracker: Detecting Prompt Injection Attacks in LLMs

NAACL 2025 Findings paper detecting prompt injection by tracking attention distribution shifts — no modification to the underlying model required, making it deployable as a wrapper on any LLM

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks and Prompt Injections

Oct 2025 paper systematically breaking 12 published defenses using gradient descent, RL, random search, and human-guided exploration. Most defenses originally claimed near-zero attack success rates; adaptive attacks exceeded 90% against all of them

The Landscape of Prompt Injection Threats in LLM Agents (SoK)

Feb 2026 systematization-of-knowledge paper with a unified taxonomy covering attack payload strategies (heuristic vs. optimisation-based) and defense intervention stages (text, model, execution). Introduces the AgentPI benchmark for context-dependent agent tasks that all prior benchmarks ignored