5 papers
Halt Fast! Early Stopping for Certified Robustness
Andrew C. Cullen, Paul Montague, Benjamin I. P. Rubinstein
Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs.…
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
Shijie Liu, Andrew C. Cullen, Paul Montague +2
The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even wri…
DynamiQ: Unlocking the Potential of Dynamic Task Allocation in Parallel Fuzzing
Wenqi Yan, Toby Murray, Benjamin I. P. Rubinstein +1
We present DynamiQ, a full-fledged and optimized successor to AFLTeam that supports dynamic and adaptive parallel fuzzing. Unlike most existing approaches that treat individual see…
Position: Certified Robustness Does Not (Yet) Imply Model Security
Andrew C. Cullen, Paul Montague, Sarah M. Erfani +1
While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be…
Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
Shijie Liu, Andrew C. Cullen, Paul Montague +2
Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets…