English
Related papers

Related papers: Building Production-Ready Probes For Gemini

200 papers

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation.…

Computation and Language · Computer Science 2025-06-02 Andrea Pedrotti , Michele Papucci , Cristiano Ciaccio , Alessio Miaschi , Giovanni Puccetti , Felice Dell'Orletta , Andrea Esuli

Generative Flow Networks (GFlowNets) are a class of generative models that sample objects in proportion to a specified reward function through a learned policy. They can be trained either on-policy or off-policy, needing a balance between…

Machine Learning · Computer Science 2025-03-04 Dominic Phillips , Flaviu Cipcigan

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Computation and Language · Computer Science 2025-11-24 Ziqi Miao , Lijun Li , Yuan Xiong , Zhenhua Liu , Pengyu Zhu , Jing Shao

Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by automating parts of the interpretation process. We evaluate four models (ChatGPT, Claude,…

Cryptography and Security · Computer Science 2025-10-22 Osama Al Haddad , Muhammad Ikram , Ejaz Ahmed , Young Lee

Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy…

Computation and Language · Computer Science 2024-10-08 Hongfu Liu , Yuxi Xie , Ye Wang , Michael Shieh

While directly fine-tuning (FT) large-scale, pretrained models on task-specific data is well-known to induce strong in-distribution task performance, recent works have demonstrated that different adaptation protocols, such as linear probing…

Machine Learning · Computer Science 2022-07-27 Puja Trivedi , Danai Koutra , Jayaraman J. Thiagarajan

Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…

Computation and Language · Computer Science 2025-01-03 Arinbjörn Kolbeinsson , Benedikt Kolbeinsson

In the highly interconnected digital landscape of today, safeguarding complex infrastructures against cyber threats has become increasingly challenging due to the exponential growth in the number and complexity of vulnerabilities. Resource…

Cryptography and Security · Computer Science 2025-02-18 Yuning Jiang , Nay Oo , Qiaoran Meng , Hoon Wei Lim , Biplab Sikdar

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Adapting state-of-the-art Large Language Models (LLMs) like GPT-4 and Gemini for specific tasks is challenging. Due to the opacity in their parameters, embeddings, and even output probabilities, existing fine-tuning adaptation methods are…

Computation and Language · Computer Science 2024-05-29 Haotian Sun , Yuchen Zhuang , Wei Wei , Chao Zhang , Bo Dai

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Computers and Society · Computer Science 2023-10-03 Joe O'Brien , Shaun Ee , Zoe Williams

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for identifying adversarial…

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate…

Human-Computer Interaction · Computer Science 2020-12-21 Darshana Rathnayake , Ashen de Silva , Dasun Puwakdandawa , Lakmal Meegahapola , Archan Misra , Indika Perera

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Qianchao Zhu , Xucheng Ye , Yuliang Liu , Haodong Ouyang , Chengru Song

As large language models (LLMs) become increasingly deployed, understanding the complexity and evolution of jailbreaking strategies is critical for AI safety. We present a mass-scale empirical analysis of jailbreak complexity across over 2…

Computation and Language · Computer Science 2026-05-28 Aldan Creo , Raul Castro Fernandez , Manuel Cebrian

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Cryptography and Security · Computer Science 2025-12-09 Tianhang Zhao , Wei Du , Haodong Zhao , Sufeng Duan , Gongshen Liu

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Xinxin Liu , Zhongliang Guo , Siyuan Huang , Chun Pong Lau

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research…

Machine Learning · Computer Science 2026-05-29 Victoria Krakovna , David Lindner , Lewis Ho , Sebastian Farquhar , Rohin Shah