CodeTracer attributes backdoored code completions to responsible fine-tuning examples via structured behavioral fingerprints, embedding retrieval, and LLM semantic reasoning under realistic post-deployment constraints.
Who taught the lie? responsibility attribution for poisoned knowledge in retrieval-augmented generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
AgentLocate localizes multi-agent LLM failures to a responsible agent and earliest decisive step via judge hypotheses, confidence-weighted multi-evaluator verification, and LoRA refinement.
citing papers explorer
-
Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions
CodeTracer attributes backdoored code completions to responsible fine-tuning examples via structured behavioral fingerprints, embedding retrieval, and LLM semantic reasoning under realistic post-deployment constraints.
-
Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems
AgentLocate localizes multi-agent LLM failures to a responsible agent and earliest decisive step via judge hypotheses, confidence-weighted multi-evaluator verification, and LoRA refinement.