Zobrazeno 1 - 10
of 73
pro vyhledávání: '"Fredrikson, Matt"'
Large language model (LLM) users might rely on others (e.g., prompting services), to write prompts. However, the risks of trusting prompts written by others remain unstudied. In this paper, we assess the risk of using such prompts on brand recommenda
Externí odkaz:
http://arxiv.org/abs/2406.04755
Autor:
Zou, Andy, Phan, Long, Wang, Justin, Duenas, Derek, Lin, Maxwell, Andriushchenko, Maksym, Wang, Rowan, Kolter, Zico, Fredrikson, Matt, Hendrycks, Dan
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 interrupts the models as they respond with harmful outputs with "circuit bre
Externí odkaz:
http://arxiv.org/abs/2406.04313
Many Internet-of-Things (IoT) devices rely on cloud computation resources to perform machine learning inferences. This is expensive and may raise privacy concerns for users. Consumers of these devices often have hardware such as gaming consoles and P
Externí odkaz:
http://arxiv.org/abs/2406.00586
Autor:
Hu, Kai, Yu, Weichen, Yao, Tianjun, Li, Xiang, Liu, Wenhe, Yu, Lijun, Li, Yining, Chen, Kai, Shen, Zhiqiang, Fredrikson, Matt
Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), w
Externí odkaz:
http://arxiv.org/abs/2405.09113
Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previous neural network models of code, such as code2seq or seq2seq, that a
Externí odkaz:
http://arxiv.org/abs/2311.13445
Autor:
Mangal, Ravi, Leino, Klas, Wang, Zifan, Hu, Kai, Yu, Weicheng, Pasareanu, Corina, Datta, Anupam, Fredrikson, Matt
Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilities posed by such attacks. Of particular interest to this paper are de
Externí odkaz:
http://arxiv.org/abs/2310.09361
Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported both theoretically and empirically, is that robustness demands greater ne
Externí odkaz:
http://arxiv.org/abs/2310.02513
Autor:
Zou, Andy, Phan, Long, Chen, Sarah, Campbell, James, Guo, Phillip, Ren, Richard, Pan, Alexander, Yin, Xuwang, Mazeika, Mantas, Dombrowski, Ann-Kathrin, Goel, Shashwat, Li, Nathaniel, Byun, Michael J., Wang, Zifan, Mallen, Alex, Basart, Steven, Koyejo, Sanmi, Song, Dawn, Fredrikson, Matt, Kolter, J. Zico, Hendrycks, Dan
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representatio
Externí odkaz:
http://arxiv.org/abs/2310.01405
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at cir
Externí odkaz:
http://arxiv.org/abs/2307.15043
Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as CIFAR-10.
Externí odkaz:
http://arxiv.org/abs/2301.12549