Is Deceptive Evolutionary Jamming Attack (DEJA) superseded?

Deceptive Evolutionary Jamming Attack (DEJA) (Retrieval-augmented generation): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by PoisonedRAG. Newer alternatives in the same sub-problem include DiscourseFlip, SilentRetrieval, Deceptive Evolutionary Jamming Attack (DEJA), LogicPoison, KEPo.

Retrieval-augmented generation

Deceptive Evolutionary Jamming Attack (DEJA)

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation

On the frontierfirst seen Apr 20, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

DiscourseFlipDiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
May 31, 2026
SilentRetrievalSilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
May 27, 2026
Deceptive Evolutionary Jamming Attack (DEJA)Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Apr 20, 2026
LogicPoisonLogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
Apr 3, 2026
KEPoKEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
Mar 12, 2026
ConfundoConfundo: Learning to Generate Robust Poison for Practical RAG Systems
Feb 6, 2026
SD-RAGSD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
Jan 16, 2026
RIPRAGRIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning
Oct 11, 2025