CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences. (arXiv:2206.00145v1 [cs.CR])

Backdoor attacks have been a critical threat to deep neural network (DNN).
However, most existing countermeasures focus on source-agnostic backdoor
attacks (SABAs) and fail to defeat source-specific backdoor attacks (SSBAs).
Compared to an SABA, an SSBA activates a backdoor when an input from
attacker-chosen class(es) is stamped with an attacker-specified trigger, making
itself stealthier and thus evade most existing backdoor mitigation.
Nonetheless, existing SSBAs have trade-offs on attack success rate (ASR, a
backdoor is activated by a trigger input from …

attacks backdoor