English
Related papers

Related papers: RL-Obfuscation: Can Language Models Learn to Evade…

200 papers

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial…

Sound · Computer Science 2026-01-01 Roee Ziv , Raz Lapid , Moshe Sipper

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

Machine Learning · Computer Science 2023-10-30 Thomas Schmied , Markus Hofmarcher , Fabian Paischer , Razvan Pascanu , Sepp Hochreiter

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical…

Computation and Language · Computer Science 2025-05-29 James Y. Huang , Wenxuan Zhou , Fei Wang , Fred Morstatter , Sheng Zhang , Hoifung Poon , Muhao Chen

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…

Cryptography and Security · Computer Science 2025-02-06 Nan Wang , Kane Walter , Yansong Gao , Alsharif Abuadbba

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 André G. Viveiros , Nuno Gonçalves , Matthias Lindemann , André Martins

Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning and inference without sacrificing performance. This is…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Moulik Choraria , Xinbo Wu , Akhil Bhimaraju , Nitesh Sekhar , Yue Wu , Xu Zhang , Prateek Singhal , Lav R. Varshney

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Naresh Kumar Devulapally , Shruti Agarwal , Tejas Gokhale , Vishnu Suresh Lokhande

Unlearning in Multimodal Large Language Models (MLLMs) prevents the model from revealing private information when queried about target images. Existing MLLM unlearning methods largely adopt approaches developed for LLMs. They treat all…

Machine Learning · Computer Science 2026-01-30 Chengyi Cai , Zesheng Ye , Peike Li , Bo Han , Jianzhong Qi , Feng Liu

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Cryptography and Security · Computer Science 2023-02-21 Marwan Omar

We explore the ability of large language models (LLMs) to engage in subtle deception through strategically phrasing and intentionally manipulating information. This harmful behavior can be hard to detect, unlike blatant lying or…

Computation and Language · Computer Science 2025-10-02 Atharvan Dogra , Krishna Pillutla , Ameet Deshpande , Ananya B Sai , John Nay , Tanmay Rajpurohit , Ashwin Kalyan , Balaraman Ravindran

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Minyoung Lee , Yeji Park , Dongjun Hwang , Yejin Kim , Seong Joon Oh , Junsuk Choe

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

Computation and Language · Computer Science 2025-06-17 Philipp Spohn , Leander Girrbach , Jessica Bader , Zeynep Akata

Large language models (LLMs) demonstrate extraordinary abilities in a wide range of natural language processing (NLP) tasks. In this paper, we show that, beyond text understanding capability, LLMs are capable of processing text layouts that…

Computation and Language · Computer Science 2024-08-29 Weiming Li , Manni Duan , Dong An , Yan Shao

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Computation and Language · Computer Science 2025-02-24 Tianlong Li , Zhenghua Wang , Wenhao Liu , Muling Wu , Shihan Dou , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang