2,077+ academic papers on AI security, attacks, and defenses
Showing 201–220 of 269 papers
Clear filtersHao Zhu, Jia Li, Cuiyun Gao +7 more
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in...
Mohammad Atif Quamar, Mohammad Areeb, Mikhail Kuznetsov +2 more
Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over...
Bryce-Allen Bagley, Navin Khoshnan
The complexity of human cognition has meant that psychology makes more use of theory and conceptual models than perhaps any other biomedical field....
Xiumei Deng, Zehui Xiong, Binbin Chen +3 more
Large language models (LLMs) are proliferating rapidly at the edge, delivering intelligent capabilities across diverse application scenarios....
Ahmad Tahmasivand, Noureldin Zahran, Saba Al-Sayouri +2 more
This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity...
Ayşe Selin Okatan, Mustafa İlhan Akbaş, Laxima Niure Kandel +1 more
We analyze subliminal transfer in Transformer models, where a teacher embeds hidden traits that can be linearly decoded by a student without...
Yifan Xia, Guorui Chen, Wenqian Yu +3 more
Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and...
Mohammed N. Swileh, Shengli Zhang
Centralized Software-Defined Networking (cSDN) offers flexible and programmable control of networks but suffers from scalability and reliability...
Md Abdul Hannan, Ronghao Ni, Chi Zhang +3 more
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of coding tasks, including summarization, translation,...
William Overman, Mohsen Bayati
As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying...
Weifei Jin, Yuxin Cao, Junjie Su +5 more
Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the...
Abha Jha, Abel Salinas, Fred Morstatter
The rise of Large Language Models (LLMs) offers transformative potential for interpreting complex legal frameworks, such as Title 18 Section 175 of...
Yiding Wang, Yuxuan Chen, Fanxu Meng +3 more
Since real-world legal experiments are often costly or infeasible, simulating legal societies with Artificial Intelligence (AI) systems provides an...
Xingyu Zhu, Beier Zhu, Shuo Wang +2 more
Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial...
Lu Liu, Wuqi Zhang, Lili Wei +3 more
Decentralized Finance (DeFi) smart contracts manage billions of dollars, making them a prime target for exploits. Price manipulation vulnerabilities,...
Nils Philipp Walter, Chawin Sitawarin, Jamie Hayes +2 more
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to...
Yulong Chen, Yadong Liu, Jiawen Zhang +3 more
Large Language Models (LLMs), despite advances in safety alignment, remain vulnerable to jailbreak attacks designed to circumvent protective...
Hanbin Hong, Ashish Kundu, Ali Payani +2 more
Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods...
Gyeonghoon Park, Jaehan Kim, Jinu Choi +1 more
Host-based cryptomining malware, commonly known as cryptojackers, have gained notoriety for their stealth and the significant financial losses they...
Roberto Brusnicki, David Pop, Yuan Gao +2 more
Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution scenarios with semantic anomalies. While Vision...
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