RAGCharacter localizes poisoned character spans in RAG evidence via prompt-conditioned counterfactual masking and achieves the best accuracy-over-attribution trade-off across tested attacks and models.
Poisoning retrieval corpora by injecting adversarial passages
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
CRAFT is a supervised LLM framework using retrieval-augmented generation, self-refinement, fine-tuning, and preference optimization to create fluent adversarial content that boosts target ranks in neural ranking models, outperforming baselines on MS MARCO and TREC benchmarks with cross-architecture
AttnTrace is an attention-weight-based context traceback method for LLMs that claims higher accuracy and efficiency than prior art like TracLLM while aiding prompt injection detection.
Introduces NPAS and AV Filter using LLM attention weights to defend RAG against poisoning, reporting up to 20% accuracy gains while adaptive attacks reach 35% success.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence
RAGCharacter localizes poisoned character spans in RAG evidence via prompt-conditioned counterfactual masking and achieves the best accuracy-over-attribution trade-off across tested attacks and models.
-
Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models
CRAFT is a supervised LLM framework using retrieval-augmented generation, self-refinement, fine-tuning, and preference optimization to create fluent adversarial content that boosts target ranks in neural ranking models, outperforming baselines on MS MARCO and TREC benchmarks with cross-architecture
-
AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
AttnTrace is an attention-weight-based context traceback method for LLMs that claims higher accuracy and efficiency than prior art like TracLLM while aiding prompt injection detection.
-
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
Introduces NPAS and AV Filter using LLM attention weights to defend RAG against poisoning, reporting up to 20% accuracy gains while adaptive attacks reach 35% success.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.