Localize-and-Detect: Auditing Task-Level Poisoning in Instruction-Tuned Models
cs.CR, cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
- The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
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