activity
20192026
most citedOn Physical Adversarial Patches for Object Detection

115 citations · 317 across the 36 of their papers we have counts for

collaborators
Showing 2024Show all

9 papers · 1 filter

cs.LG2024

Understanding Optimization in Deep Learning with Central Flows

Jeremy M. Cohen, Alex Damian, Ameet Talwalkar +2

Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that opti…

cs.LG2024★ 5 cited

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian +11

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as s…

cs.LG2024★ 7 cited

Improving Alignment and Robustness with Circuit Breakers

Andy Zou, Long Phan, Justin Wang +7

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interr…

cs.CV2024

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers

Swaminathan Gurumurthy, Karnik Ram, Bingqing Chen +2

Various pose estimation and tracking problems in robotics can be decomposed into a correspondence estimation problem (often computed using a deep network) followed by a weighted le…

cs.LG2024

Why is SAM Robust to Label Noise?

Christina Baek, Zico Kolter, Aditi Raghunathan

Sharpness-Aware Minimization (SAM) is most known for achieving state-of the-art performances on natural image and language tasks. However, its most pronounced improvements (of tens…

cs.LG2024★ 2 cited

Neural Network Verification with Branch-and-Bound for General Nonlinearities

Zhouxing Shi, Qirui Jin, Zico Kolter +3

Branch-and-bound (BaB) is among the most effective techniques for neural network (NN) verification. However, existing works on BaB for NN verification have mostly focused on NNs wi…