DSR decomposes harmful intents into benign textual and visual primitives that MLLMs fuse into harmful outputs, achieving high attack success with low input toxicity.
arXiv preprint arXiv:2412.05934
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
PRISM decomposes harmful instructions into benign visual gadgets and directs LVLMs via prompts to compose them through reasoning into harmful outputs, achieving ASR over 0.90 on SafeBench.
AuthChain poisons a single document to achieve high-success attacks on RAG systems for multi-hop queries across six LLMs while evading defenses.
citing papers explorer
-
Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition
DSR decomposes harmful intents into benign textual and visual primitives that MLLMs fuse into harmful outputs, achieving high attack success with low input toxicity.
-
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
PRISM decomposes harmful instructions into benign visual gadgets and directs LVLMs via prompts to compose them through reasoning into harmful outputs, achieving ASR over 0.90 on SafeBench.
-
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
AuthChain poisons a single document to achieve high-success attacks on RAG systems for multi-hop queries across six LLMs while evading defenses.