Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Shi, Zhouxing"'
In recent years, many neural network (NN) verifiers have been developed to formally verify certain properties of neural networks such as robustness. Although many benchmarks have been constructed to evaluate the performance of NN verifiers, they typi
Externí odkaz:
http://arxiv.org/abs/2412.03154
We study the problem of learning Lyapunov-stable neural controllers which provably satisfy the Lyapunov asymptotic stability condition within a region-of-attraction. Compared to previous works which commonly used counterexample guided training on thi
Externí odkaz:
http://arxiv.org/abs/2411.18235
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 with piecewise linear activations, especially ReLU networks. In this pap
Externí odkaz:
http://arxiv.org/abs/2405.21063
Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. However, formal (Lyapunov) stability guarantees over the region-of-attraction (ROA) for NN controllers w
Externí odkaz:
http://arxiv.org/abs/2404.07956
Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new method for def
Externí odkaz:
http://arxiv.org/abs/2402.16459
The strong general capabilities of Large Language Models (LLMs) bring potential ethical risks if they are unrestrictedly accessible to malicious users. Token-level watermarking inserts watermarks in the generated texts by altering the token probabili
Externí odkaz:
http://arxiv.org/abs/2311.09668
The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to detect LLM
Externí odkaz:
http://arxiv.org/abs/2305.19713
Autor:
Shi, Zhouxing, Carlini, Nicholas, Balashankar, Ananth, Schmidt, Ludwig, Hsieh, Cho-Jui, Beutel, Alex, Qin, Yao
"Effective robustness" measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as ImageNet to evalu
Externí odkaz:
http://arxiv.org/abs/2302.01381
Lipschitz constants are connected to many properties of neural networks, such as robustness, fairness, and generalization. Existing methods for computing Lipschitz constants either produce relatively loose upper bounds or are limited to small network
Externí odkaz:
http://arxiv.org/abs/2210.07394
Interval Bound Propagation (IBP) is so far the base of state-of-the-art methods for training neural networks with certifiable robustness guarantees when potential adversarial perturbations present, while the convergence of IBP training remains unknow
Externí odkaz:
http://arxiv.org/abs/2203.08961