Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic

Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic arXiv:2606.20254v1 Announce Type: new Abstract: Model quantization is widely adopted to reduce memory usage and inference cost when deploying deep neural networks on resource-constrained devices. However, recent studies have revealed a new security threat known as Quantization-Conditioned Backdoors (QCBs), where a model behaves normally in full precision but activates malicious …

https://arxiv.org/abs/2606.20254

sha256:180972d812cf9b96d13a8d2716828ffbcca3adfb67b744afa4f9984bfc0717ea

• cve0
• md50
• url0
• ipv40
• ipv60
• sha10
• domain0
• sha2560
• malware_token0
• attack_pattern0
• threat_actor_token0