Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
baseline 1polarities
baseline 1representative citing papers
Argus enables backdoor detection in decentralized ML by collaborative neighbor-based validation of triggers, backed by convergence theory and reducing attack success by up to 90% on tested datasets.
Gungnir shows that style-based triggers with RAN and STTR techniques can activate backdoors in diffusion models while evading detection and surviving fine-tuning.
The paper defines defeat devices in AI via a triadic test (discriminator, concealed swap, performance gap), unifies existing cases under this concept, proposes TADP detection, and claims such devices can emerge naturally in frontier models.
GLA backdoor attack on DriveVLM uses naturalistic graffiti and cross-lingual triggers to reach 90% ASR at 10% poisoning ratio while improving some clean-task metrics like BLEU-1.
TEMPO-Diffusion is a targeted backdoor attack framework for diffusion models that uses time-conditioned triggers to poison class-specific synthetic data, achieving high attack success in downstream classifiers.
citing papers explorer
-
Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
-
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
Argus enables backdoor detection in decentralized ML by collaborative neighbor-based validation of triggers, backed by convergence theory and reducing attack success by up to 90% on tested datasets.
-
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
Gungnir shows that style-based triggers with RAN and STTR techniques can activate backdoors in diffusion models while evading detection and surviving fine-tuning.
-
Defeat Devices in AI Systems
The paper defines defeat devices in AI via a triadic test (discriminator, concealed swap, performance gap), unifies existing cases under this concept, proposes TADP detection, and claims such devices can emerge naturally in frontier models.
-
Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
GLA backdoor attack on DriveVLM uses naturalistic graffiti and cross-lingual triggers to reach 90% ASR at 10% poisoning ratio while improving some clean-task metrics like BLEU-1.
-
TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models
TEMPO-Diffusion is a targeted backdoor attack framework for diffusion models that uses time-conditioned triggers to poison class-specific synthetic data, achieving high attack success in downstream classifiers.