Transaction

0dbaff31e41ed1fa31f1e78c3eee444dbbd4f4d91a2ea501358cdbdaaecbb4eb
Timestamp (utc)
2024-08-27 07:16:21
Fee Paid
0.00000006 BSV
(
0.00312140 BSV
-
0.00312134 BSV
)
Fee Rate
2.591 sat/KB
Version
1
Confirmations
75,700
Size Stats
2,315 B

3 Outputs

Total Output:
0.00312134 BSV
  • jmetaB03d330435ab850f3d6163ec4853dc1ce572fc415dc0b065fd7503daf9b27ee1407@104e04f4dc7bbb58b675a0be8ec8a2392cd828cadc0c1b85347e2d4ab003150erss.item metarss.netM{<item> <title>Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks</title> <link>https://arxiv.org/abs/2401.15295</link> <description>arXiv:2401.15295v2 Announce Type: replace-cross Abstract: Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely on identifying and eliminating the ``shortcut" created by the backdoor, which links a specific source class to a target class. However, these approaches can be easily circumvented by designing multiple backdoor triggers that create shortcuts everywhere and therefore nowhere specific. In this study, we explore the concept of Multi-Trigger Backdoor Attacks (MTBAs), where multiple adversaries leverage different types of triggers to poison the same dataset. By proposing and investigating three types of multi-trigger attacks including \textit{parallel}, \textit{sequential}, and \textit{hybrid} attacks, we demonstrate that 1) multiple triggers can coexist, overwrite, or cross-activate one another, and 2) MTBAs easily break the prevalent shortcut assumption underlying most existing backdoor detection/removal methods, rendering them ineffective. Given the security risk posed by MTBAs, we have created a multi-trigger backdoor poisoning dataset to facilitate future research on detecting and mitigating these attacks, and we also discuss potential defense strategies against MTBAs.</description> <guid isPermaLink="false">oai:arXiv.org:2401.15295v2</guid> <category>cs.LG</category> <category>cs.CR</category> <pubDate>Tue, 27 Aug 2024 00:00:00 -0400</pubDate> <arxiv:announce_type>replace-cross</arxiv:announce_type> <dc:rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0/</dc:rights> <dc:creator>Yige Li, Jiabo He, Hanxun Huang, Jun Sun, Xingjun Ma</dc:creator> </item>
    https://whatsonchain.com/tx/0dbaff31e41ed1fa31f1e78c3eee444dbbd4f4d91a2ea501358cdbdaaecbb4eb