2,077+ academic papers on AI security, attacks, and defenses
Showing 621–640 of 2,077 papers
Mingrui Liu, Sixiao Zhang, Cheng Long +1 more
Large Language Models (LLMs) are increasingly vulnerable to Prompt Injection (PI) attacks, where adversarial instructions hidden within retrieved...
Yilin Geng, Omri Abend, Eduard Hovy +1 more
It is not only what we ask large language models (LLMs) to do that matters, but also how we prompt. Phrases like "This is urgent" or "As your...
Pengyu Li, Lingling Zhang, Zhitao Gao +5 more
While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and...
Seyed Mohammad Hadi Hosseini, Amir Najafi, Mahdieh Soleymani Baghshah
Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large...
Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu +1 more
Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of malicious queries. We argue that this...
Zehua Cheng, Jianwei Yang, Wei Dai +1 more
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for...
Haobo Wang, Weiqi Luo, Xiaojun Jia +1 more
Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models...
Xiaoyu Wen, Zhida He, Han Qi +7 more
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due...
Yangfan Deng, Anirudh Nakra, Min Wu
3D content acquisition and creation are expanding rapidly in the new era of machine learning and AI. 3D Gaussian Splatting (3DGS) has become a...
Max Manolov, Tony Gao, Siddharth Shukla +2 more
Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often...
Poushali Sengupta, Shashi Raj Pandey, Sabita Maharjan +1 more
Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved...
Eliron Rahimi, Elad Hirshel, Rom Himelstein +3 more
Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) models, offering parallel decoding and...
Ziyue Wang, Jiangshan Yu, Kaihua Qin +3 more
Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without...
Shaowei Shen, Xiaohong Yang, Jie Yang +4 more
Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for...
Shaowei Shen, Xiaohong Yang, Jie Yang +4 more
Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for...
Terry Yue Zhuo, Yangruibo Ding, Wenbo Guo +1 more
For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at...
Chengran Yang, Zichao Wei, Heminghao Deng +6 more
Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an...
Abhilekh Borah, Shubhra Ghosh, Kedar Joshi +2 more
Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in...
Xinyi Hou, Shenao Wang, Yifan Zhang +4 more
Agentic AI systems built around large language models (LLMs) are moving away from closed, single-model frameworks and toward open ecosystems that...
Kaiyuan Cui, Yige Li, Yutao Wu +4 more
Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text....
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert