CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
cs.CR
Submitted: 2025-11-27
Updated: 2026-09-15
Comments: Accepted for publication at the IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2026
Code: https://github.com/ML-Security-Research-LAB/CacheTrap
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Challenges and Applications of Large Language Models
- Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs
- SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models
- SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
- FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning
- MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems
- RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
- An Open Multilingual System for Scoring Readability of Wikipedia
- Layer-Condensed KV Cache for Efficient Inference of Large Language Models
- Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
- Massive Activations in Large Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- The Llama 3 Herd of Models
- Mistral 7B
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
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