Goto

Collaborating Authors

 poisoning



Russia rejects claims of poisoning Navalny with dart frog toxin

Al Jazeera

The Kremlin has "strongly" rejected an assessment by five European countries that the Russian state killed jailed opposition leader Alexey Navalny by poisoning him. Navalny, President Vladimir Putin's fiercest domestic opponent for years, died in an Arctic prison colony on February 16, 2024 while serving a 19-year sentence for "extremism", a charge he and his supporters said was punishment for his opposition work. "We naturally do not accept such accusations. We consider them biased and baseless," Kremlin spokesman Dmitry Peskov told reporters during a daily briefing call on Monday. "In fact, we strongly reject them," he added.


BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking Bin Huang 1 Jiaqian Y u

Neural Information Processing Systems

Visual object tracking (VOT) is one of the most fundamental tasks in computer vision community. State-of-the-art VOT trackers extract positive and negative examples that are used to guide the tracker to distinguish the object from the background. In this paper, we show that this characteristic can be exploited to introduce new threats and hence propose a simple yet effective poison-only backdoor attack.




Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder

Ji Feng, Qi-Zhi Cai, Zhi-Hua Zhou

Neural Information Processing Systems

Thiscanbe formulated into anon-linear equality constrained optimization problem. Unlike GANs, solving such problem iscomputationally challenging, wethen proposed a simple yet effective procedure to decouple the alternating updates for the two networks for stability. By teaching the perturbation generator to hijacking the training trajectory of the victim classifier, the generator can thus learn to move against thevictim classifier stepbystep.





90cc440b1b8caa520c562ac4e4bbcb51-Paper.pdf

Neural Information Processing Systems

Unsupervised domain adaptation (UDA)enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs from that of the target. However, UDA is not always successful and several accounts of'negative transfer' have been reported in the literature.