We have 2 of 4 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is shown that the same feature-learning dynamics that make neural networks powerful can also make them more vulnerable to backdoors, and that security audits based on linear heuristics can systematically underestimate backdoor vulnerability in the widely adopted feature-learning regimes.
It is proved that the success probability of any bounded adversary asymptotically collapses to zero under a defense strategy combining natural absorption, a randomized scheduler, and lazy verification oracle, which yields a provably sound and computationally efficient defense for safety-critical AI.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
