2,583+ academic papers on AI security, attacks, and defenses
Showing 1881–1900 of 2,583 papers
Wei Zhao, Zhe Li, Yige Li +1 more
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial...
Huseein Jawad, Nicolas Brunel
System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive...
Yijun Yang, Lichao Wang, Jianping Zhang +3 more
The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and...
Yige Li, Zhe Li, Wei Zhao +4 more
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors...
Strahinja Janjusevic, Anna Baron Garcia, Sohrob Kazerounian
Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests....
Samih Fadli
Large language model safety is usually assessed with static benchmarks, but key failures are dynamic: value drift under distribution shift, jailbreak...
Zhaoxin Zhang, Borui Chen, Yiming Hu +3 more
Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful...
Zhihan Ren, Lijun He, Jiaxi Liang +3 more
Split DNNs enable edge devices by offloading intensive computation to a cloud server, but this paradigm exposes privacy vulnerabilities, as the...
Piercosma Bisconti, Matteo Prandi, Federico Pierucci +7 more
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25...
Badrinath Ramakrishnan, Akshaya Balaji
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant...
Bui Duc Son, Trinh Van Chien, Dong In Kim
The integration of generative artificial intelligence (GenAI) into 6G networks promises substantial performance gains while simultaneously exposing...
Zimo Ji, Xunguang Wang, Zongjie Li +6 more
Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt...
Jingzhuo Zhou
The rapid proliferation of Multimodal Large Language Models (MLLMs) has introduced unprecedented security challenges, particularly in phishing...
Saeefa Rubaiyet Nowmi, Jesus Lopez, Md Mahmudul Alam Imon +2 more
Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering improved representational capacity and...
W. Bradley Knox, Katie Bradford, Samanta Varela Castro +6 more
Amid the growing prevalence of human-AI interaction, large language models and other AI-based entities increasingly provide forms of companionship to...
Henry Wong, Clement Fung, Weiran Lin +3 more
To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom...
Fu-Ming Guo, Yingfang Fan
Adaptive optimizers with decoupled weight decay, such as AdamW, are the de facto standard for pre-training large transformer-based generative models....
Abolfazl Younesi, Leon Kiss, Zahra Najafabadi Samani +2 more
Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who...
Xin Yi, Yue Li, Dongsheng Shi +3 more
Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning...
Zhengchunmin Dai, Jiaxiong Tang, Peng Sun +2 more
In decentralized machine learning paradigms such as Split Federated Learning (SFL) and its variant U-shaped SFL, the server's capabilities are...
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