AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

arXiv:2609.06972 · cs.CR, cs.AI, cs.LG · Submitted 2026-09-07 · Read on arXiv

cs.CR, cs.AI, cs.LG

Submitted: 2026-09-07

Updated: 2026-09-07

Comments: 19 pages, 8 figures, 13 tables. Dataset: https://github.com/Asif-0209/AgentDrift

Code: https://github.com/Asif-0209/AgentDrift

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

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