Zobrazeno 1 - 10
of 416
pro vyhledávání: '"MCDANIEL, PATRICK"'
Autor:
Liu, Xiaogeng, Li, Peiran, Suh, Edward, Vorobeychik, Yevgeniy, Mao, Zhuoqing, Jha, Somesh, McDaniel, Patrick, Sun, Huan, Li, Bo, Xiao, Chaowei
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), a
Externí odkaz:
http://arxiv.org/abs/2410.05295
Autor:
Hoak, Blaine, McDaniel, Patrick
The influence of textures on machine learning models has been an ongoing investigation, specifically in texture bias/learning, interpretability, and robustness. However, due to the lack of large and diverse texture data available, the findings in the
Externí odkaz:
http://arxiv.org/abs/2409.10297
Autor:
King, Rachel, Burke, Quinn, Beugin, Yohan, Hoak, Blaine, Li, Kunyang, Pauley, Eric, Sheatsley, Ryan, McDaniel, Patrick
The Tor anonymity network allows users such as political activists and those under repressive governments to protect their privacy when communicating over the internet. At the same time, Tor has been demonstrated to be vulnerable to several classes o
Externí odkaz:
http://arxiv.org/abs/2408.14646
Merkle hash trees are the state-of-the-art method to protect the integrity of storage systems. However, using a hash tree can severely degrade performance, and prior works optimizing them have yet to yield a concrete understanding of the scalability
Externí odkaz:
http://arxiv.org/abs/2405.03830
Autor:
Beugin, Yohan, McDaniel, Patrick
The Topics API for the web is Google's privacy-enhancing alternative to replace third-party cookies. Results of prior work have led to an ongoing discussion between Google and research communities about the capability of Topics to trade off both util
Externí odkaz:
http://arxiv.org/abs/2403.19577
Autor:
Hoak, Blaine, McDaniel, Patrick
In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about
Externí odkaz:
http://arxiv.org/abs/2403.09543
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also increasing conce
Externí odkaz:
http://arxiv.org/abs/2402.18649
Autor:
Wang, Jiongxiao, Li, Jiazhao, Li, Yiquan, Qi, Xiangyu, Hu, Junjie, Li, Yixuan, McDaniel, Patrick, Chen, Muhao, Li, Bo, Xiao, Chaowei
Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats, particularly a
Externí odkaz:
http://arxiv.org/abs/2402.14968
Signature-based Intrusion Detection Systems (SIDSs) are traditionally used to detect malicious activity in networks. A notable example of such a system is Snort, which compares network traffic against a series of rules that match known exploits. Curr
Externí odkaz:
http://arxiv.org/abs/2402.09644
Today, the security of many domains rely on the use of Machine Learning to detect threats, identify vulnerabilities, and safeguard systems from attacks. Recently, transformer architectures have improved the state-of-the-art performance on a wide rang
Externí odkaz:
http://arxiv.org/abs/2310.11597