The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper reports two data‑only poisoning attacks on protein design systems. In the first, poisoned sequences were added to the pre‑training corpus of large autoregressive language models, causing the models to reliably generate sequences triggered by specific patterns after as few as 200 contaminated examples. The second attack inserted malicious records into a retrieval corpus, enabling a single query‑aware record to dominate retrieval results and, in many cases, alter the generated protein sequence or transfer a new domain via homology.
arXiv:2606. 11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection.
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector...
arXiv:2603. 22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface.
arXiv:2604.22117v3 Announce Type: replace-cross Abstract: Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a sub...
arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.