SilentCall: Hidden Tool-Call Backdoors in Open-Weight Agents, and How to Catch Them
cs.CR, cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/ggml-org/llama.cpp
Terminology
Sources
- MathArena: Evaluating LLMs on Uncontaminated Math Competitions
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Measuring Massive Multitask Language Understanding
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
- CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
- Universal Jailbreak Backdoors from Poisoned Human Feedback
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
- OJBench: A Competition Level Code Benchmark For Large Language Models
- Qwen3 Technical Report
- Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
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