Year: 2026
Type: conference-paper
Abstract: We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for adversarial objectives such as RAG poisoning, jailbreaking, and evasion of defensive filters.Prior generation methods either produce easily detectable gibberish (even methods that optimize for low perplexity), or cannot handle objectives that include embedding similarity.In particular, they cannot produce readable adversarial documents that (1) are retrieved by RAG systems in response to broad classes of queries, and (2) adversarially influence subsequent generation.We measure the effectiveness of adversarial decoding for different objectives and demonstrate that it outperforms existing methods while producing adversarial documents that cannot be automatically distinguished from natural documents by fluency and readability.
Authors: Collin Zhang, Tingwei Zhang, Vitaly Shmatikov
Institution: Cornell University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140117835