2,077+ academic papers on AI security, attacks, and defenses
Showing 201–220 of 2,077 papers
Punyajoy Saha, Sudipta Halder, Debjyoti Mondal +1 more
Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large...
Ondřej Lukáš, Jihoon Shin, Emilia Rivas +6 more
Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift --...
Zheng Yu, Wenxuan Shi, Xinqian Sun +3 more
Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in...
Zheng Yu, Wenxuan Shi, Xinqian Sun +3 more
Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in...
Elzo Brito dos Santos Filho
AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are...
Donghwa Kang, Hojun Choe, Doohyun Kim +2 more
Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN...
Yanbang Sun, Quan Luo, Yuelin Wang +6 more
Network protocols are the foundation of modern communication, yet their implementations often contain semantic vulnerabilities stemming from...
Xisen Jin, Michael Duan, Qin Lin +4 more
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces...
Jinman Wu, Yi Xie, Shen Lin +2 more
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the...
Jinman Wu, Yi Xie, Shiqian Zhao +1 more
Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights...
Ved Sriraman, Adam Block
Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a...
Amirpasha Mozaffari, Amanda Duarte, Lina Teckentrup +8 more
The rapid adoption of AI in Earth system science promises unprecedented speed and fidelity in the generation of climate information. However, this...
Touseef Hasan, Blessing Airehenbuwa, Nitin Pundir +2 more
Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security...
Junchuan Zhao, Minh Duc Vu, Ye Wang
Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and...
Xiaoguang Li, Hanyi Wang, Yaowei Huang +6 more
Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from...
Anatoly Belikov, Ilya Fedotov
Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe KV...
Trapoom Ukarapol, Nut Chukamphaeng, Kunat Pipatanakul +1 more
The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded...
Minjune Hwang, Yigit Korkmaz, Daniel Seita +1 more
Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it...
Yuchen Shi, Huajie Chen, Heng Xu +6 more
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources....
Yuanbo Li, Tianyang Xu, Cong Hu +3 more
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also...
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