The Blind Spots of Detection: Adversarial Perturbation Attacks against Watchdogs in Distributed LLM Inference
cs.CR
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization
- Evaluating Large Language Models Trained on Code
- Integrity of peer-to-peer distributed LLM inference under malicious nodes
- Training Verifiers to Solve Math Word Problems
- SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training
- Scaling Laws for Adversarial Attacks on Language Model Activations
- Gemma 4 Technical Report
- LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
- Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
- DiFR: Inference Verification Despite Nondeterminism
- Programming Refusal with Conditional Activation Steering
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- Prompt Inference Attack on Distributed Large Language Model Inference Frameworks
- Prompt Inversion Attack against Collaborative Inference of Large Language Models
- PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
- SVIP: Towards Verifiable Inference of Open-source Large Language Models
- Muse Glimmer 30B: An On-Device Agentic Model
- Parallax: Efficient LLM Inference Service over Decentralized Environment
- Attention Is All You Need
- VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data