The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security
cs.CR, cs.CL
Submitted: 2026-10-03
Updated: 2026-10-03
Sources
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
- When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
- LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review
- EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
- Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
- An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping
- Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory
- Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning
- LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs