Zobrazeno 1 - 10
of 600
pro vyhledávání: '"Chen, Yanjiao"'
Autor:
Gong, Xueluan, Li, Mingzhe, Zhang, Yilin, Ran, Fengyuan, Chen, Chen, Chen, Yanjiao, Wang, Qian, Lam, Kwok-Yan
Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either rely
Externí odkaz:
http://arxiv.org/abs/2409.14866
Autor:
Deng, Jiangyi, Li, Xinfeng, Chen, Yanjiao, Bai, Yijie, Weng, Haiqin, Liu, Yan, Wei, Tao, Xu, Wenyuan
Malicious shell commands are linchpins to many cyber-attacks, but may not be easy to understand by security analysts due to complicated and often disguised code structures. Advances in large language models (LLMs) have unlocked the possibility of gen
Externí odkaz:
http://arxiv.org/abs/2409.02074
Autor:
Wu, Jialin, Deng, Jiangyi, Pang, Shengyuan, Chen, Yanjiao, Xu, Jiayang, Li, Xinfeng, Xu, Wenyuan
Given the societal impact of unsafe content generated by large language models (LLMs), ensuring that LLM services comply with safety standards is a crucial concern for LLM service providers. Common content moderation methods are limited by an effecti
Externí odkaz:
http://arxiv.org/abs/2408.15488
Autor:
Deng, Jiangyi, Pang, Shengyuan, Chen, Yanjiao, Xia, Liangming, Bai, Yijie, Weng, Haiqin, Xu, Wenyuan
Instead of building deep learning models from scratch, developers are more and more relying on adapting pre-trained models to their customized tasks. However, powerful pre-trained models may be misused for unethical or illegal tasks, e.g., privacy in
Externí odkaz:
http://arxiv.org/abs/2404.12699
Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW
Externí odkaz:
http://arxiv.org/abs/2404.06666
Voice conversion (VC) techniques can be abused by malicious parties to transform their audios to sound like a target speaker, making it hard for a human being or a speaker verification/identification system to trace the source speaker. In this paper,
Externí odkaz:
http://arxiv.org/abs/2302.12434
Voice data generated on instant messaging or social media applications contains unique user voiceprints that may be abused by malicious adversaries for identity inference or identity theft. Existing voice anonymization techniques, e.g., signal proces
Externí odkaz:
http://arxiv.org/abs/2210.15140
Autor:
Tachega, Mark Awe, Chen, Yanjiao, Agbanyo, George Kwame, Ahmed, Rizwan, Appiah, Augustine, Mintah, Clement
Publikováno v:
In Energy 30 October 2024 307
Millimeter-wave (mmWave) radars have found applications in a wide range of domains, including human tracking, health monitoring, and autonomous driving, for their unobtrusive nature and high range accuracy. These capabilities, however, if used for ma
Externí odkaz:
http://arxiv.org/abs/2201.03336