English
Related papers

Related papers: CAPTURE: Context-Aware Prompt Injection Testing an…

200 papers

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey

The increasing deployment of large language models in security-sensitive domains necessitates rigorous evaluation of their resilience against adversarial prompt-based attacks. While previous benchmarks have focused on security evaluations…

Cryptography and Security · Computer Science 2025-09-22 Huining Cui , Wei Liu

AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show…

Cryptography and Security · Computer Science 2026-03-24 Rishika Bhagwatkar , Kevin Kasa , Abhay Puri , Gabriel Huang , Irina Rish , Graham W. Taylor , Krishnamurthy Dj Dvijotham , Alexandre Lacoste

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

Artificial Intelligence · Computer Science 2026-05-28 Dasol Choi , Alex Kwon

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Machine Learning · Computer Science 2025-08-28 Dylan Sam , Alexander Robey , Andy Zou , Matt Fredrikson , J. Zico Kolter

Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length…

Computation and Language · Computer Science 2022-12-14 Yaru Hao , Yutao Sun , Li Dong , Zhixiong Han , Yuxian Gu , Furu Wei

Retrieval-augmented generation has gained popularity as a framework to enhance large language models with external knowledge. However, its effectiveness hinges on the retrieval robustness of the model. If the model lacks retrieval…

Computation and Language · Computer Science 2024-06-27 Xiaoyu Shen , Rexhina Blloshmi , Dawei Zhu , Jiahuan Pei , Wei Zhang

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

Computation and Language · Computer Science 2026-03-23 Naseem Machlovi , Maryam Saleki , Ruhul Amin , Mohamed Rahouti , Shawqi Al-Maliki , Junaid Qadir , Mohamed M. Abdallah , Ala Al-Fuqaha

The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has…

Computation and Language · Computer Science 2019-03-07 Mathias Müller , Annette Rios , Elena Voita , Rico Sennrich

Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Ritabrata Chakraborty , Shivakumara Palaiahnakote , Umapada Pal , Cheng-Lin Liu

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific…

Computation and Language · Computer Science 2025-05-21 Ruobing Yao , Yifei Zhang , Shuang Song , Neng Gao , Chenyang Tu

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Cryptography and Security · Computer Science 2024-01-03 Daniel Wankit Yip , Aysan Esmradi , Chun Fai Chan

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Computation and Language · Computer Science 2024-12-20 Barys Liskavets , Maxim Ushakov , Shuvendu Roy , Mark Klibanov , Ali Etemad , Shane Luke

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Chia-Wen Kuo , Zsolt Kira

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a…

Machine Learning · Computer Science 2020-12-16 Haotian Fu , Hongyao Tang , Jianye Hao , Chen Chen , Xidong Feng , Dong Li , Wulong Liu

Current safety mechanisms for Large Language Models (LLMs) rely heavily on static, fine-tuned classifiers that suffer from adaptation rigidity, the inability to enforce new governance rules without expensive retraining. To address this, we…

Artificial Intelligence · Computer Science 2026-02-27 Umid Suleymanov , Rufiz Bayramov , Suad Gafarli , Seljan Musayeva , Taghi Mammadov , Aynur Akhundlu , Murat Kantarcioglu

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…

Machine Learning · Computer Science 2026-05-29 Indranil Halder , Annesya Banerjee , Cengiz Pehlevan

Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Yousuf Ahmed Siddiqui , Sufiyaan Usmani , Umer Tariq , Jawwad Ahmed Shamsi , Muhammad Burhan Khan