2,104+ academic papers on AI security, attacks, and defenses
Showing 561–580 of 2,029 papers
Clear filtersAbdullah Arafat Miah, Kevin Vu, Yu Bi
Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as information is...
Shang Liu, Hanyu Pei, Zeyan Liu
Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes....
Saad Hossain, Tom Tseng, Punya Syon Pandey +8 more
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications,...
Chen Chen, Yuchen Sun, Jiaxin Gao +4 more
Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However,...
Zhuoheng Li, Ying Chen
Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse...
Mingqian Feng, Xiaodong Liu, Weiwei Yang +4 more
Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing...
Yassine Chagna, Antal Goldschmidt
This project explores large language models (LLMs) for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems...
Fengpeng Li, Kemou Li, Qizhou Wang +2 more
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off....
Yunlong Lyu, Yixuan Tang, Peng Chen +4 more
Modern AI-integrated IDEs are shifting from passive code completion to proactive Next Edit Suggestions (NES). Unlike traditional autocompletion, NES...
Ying Song, Balaji Palanisamy
Graph-structured data underpin a wide spectrum of modern applications. However, complex graph topologies and homophilic patterns can facilitate...
Li Lu, Yanjie Zhao, Hongzhou Rao +2 more
Large Language Models (LLMs) have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists:...
Mengyao Du, Han Fang, Haokai Ma +4 more
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes...
Haoyang Hu, Zhejun Jiang, Yueming Lyu +3 more
Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear...
Yi Liu, Zhihao Chen, Yanjun Zhang +5 more
Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user...
Hema Karnam Surendrababu, Nithin Nagaraj
Machine Learning (ML) models, including Large Language Models (LLMs), are characterized by a range of system-level attributes such as security and...
Haipeng Li, Rongxuan Peng, Anwei Luo +3 more
The rapid advancement of AI-Generated Content (AIGC) technologies poses significant challenges for authenticity assessment. However, existing...
Minkyoo Song, Jaehan Kim, Myungchul Kang +3 more
Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with...
Sung-Hoon Yoon, Ruizhi Qian, Minda Zhao +2 more
Large Language Models (LLMs) have become integral to many domains, making their safety a critical priority. Prior jailbreaking research has explored...
Guowei Guan, Yurong Hao, Jiaming Zhang +6 more
Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal...
Mona Rajhans, Vishal Khawarey
Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention....
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