4 papers
Energy-Latency Attacks via Sponge Poisoning
Antonio Emanuele CinÃ, Ambra Demontis, Battista Biggio +2
Sponge examples are test-time inputs optimized to increase energy consumption and prediction latency of deep networks deployed on hardware accelerators. By increasing the fraction…
On generalized KKT points for the Motzkin-Straus program
G. Beretta, A. Torcinovich, M. Pelillo
In 1965, T. S. Motzkin and E. G. Straus established an elegant connection between the clique number of a graph and the global maxima of a quadratic program defined on the standard…
Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
Antonio Emanuele CinÃ, Kathrin Grosse, Sebastiano Vascon +4
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at…
Nash Meets Wertheimer: Using Good Continuation in Jigsaw Puzzles
Marina Khoroshiltseva, Luca Palmieri, Sinem Aslan +2
Jigsaw puzzle solving is a challenging task for computer vision since it requires high-level spatial and semantic reasoning. To solve the problem, existing approaches invariably us…