2,529+ academic papers on AI security, attacks, and defenses
Showing 61–80 of 222 papers
Clear filtersXisen 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...
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...
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...
Zeyu Zhang, Xiangxiang Dai, Ziyi Han +2 more
Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during...
Manisha Mukherjee, Vincent J. Hellendoorn
Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in...
Ming Wen, Kun Yang, Xin Chen +4 more
Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as...
Chang Xue, Fang Liu, Jiaye Wang +2 more
Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized...
Lan Zhang, Chengsi Liang, Zeming Zhuang +4 more
Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this...
Xuan Chen, Hao Liu, Tao Yuan +3 more
Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent...
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4 more
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct...
Morteza Eskandarian, Mahdi Rabbani, Arun Kaniyamattam +6 more
The current generation of large language models produces sophisticated social-engineering content that bypasses standard text screening systems in...
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav +4 more
Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when...
Zachary Coalson, Beth Sohler, Aiden Gabriel +1 more
We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches...
Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami +1 more
Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight...
Ahmed Ryan, Ibrahim Khalil, Abdullah Al Jahid +4 more
The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large...
David Puertolas Merenciano, Ekaterina Vasyagina, Raghav Dixit +4 more
LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging...
Tianyu Chen, Dongrui Liu, Xia Hu +2 more
Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises...
George Alexandru Adam, Alexander Cui, Edwin Thomas +7 more
While historical considerations surrounding text authenticity revolved primarily around plagiarism, the advent of large language models (LLMs) has...
Zhaoxin Wang, Jiaming Liang, Fengbin Zhu +5 more
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent...
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