English
Related papers

Related papers: Universal Adversarial Suffixes Using Calibrated Gu…

200 papers

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

Machine Learning · Computer Science 2026-05-20 Mohammed Alshaalan , Miguel R. D. Rodrigues

Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their…

Sound · Computer Science 2024-10-14 Vyas Raina , Mark Gales

State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length,…

Computation and Language · Computer Science 2019-09-04 Robin Jia , Aditi Raghunathan , Kerem Göksel , Percy Liang

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

Machine Learning · Computer Science 2021-06-15 Dara Bahri , Heinrich Jiang

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick…

Computation and Language · Computer Science 2020-09-18 Pepa Atanasova , Dustin Wright , Isabelle Augenstein

Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word…

Computation and Language · Computer Science 2017-11-20 Raphael Shu , Hideki Nakayama

Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and…

Machine Learning · Computer Science 2023-07-06 Yeqi Gao , Zhao Song , Shenghao Xie

This paper introduces a framework that connects a deep generative pre-trained Transformer language model with a generative adversarial network for semi-supervised text generation. In other words, the proposed model is first pre-trained…

Computation and Language · Computer Science 2025-02-11 Shengquan Wang

Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Ali Shafahi , Mahyar Najibi , Zheng Xu , John Dickerson , Larry S. Davis , Tom Goldstein

As language models scale, their performance improves dramatically across a wide range of tasks, but so does their tendency to memorize and regurgitate parts of their training data verbatim. This tradeoff poses serious legal, ethical, and…

Machine Learning · Computer Science 2025-05-28 Parjanya Prajakta Prashant , Kaustubh Ponkshe , Babak Salimi

Recognizing emotions in spoken communication is crucial for advanced human-machine interaction. Current emotion detection methodologies often display biases when applied cross-corpus. To address this, our study amalgamates 16 diverse…

Computation and Language · Computer Science 2023-11-16 Mohamed Osman , Tamer Nadeem , Ghada Khoriba

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ruofan Wang , Xingjun Ma , Hanxu Zhou , Chuanjun Ji , Guangnan Ye , Yu-Gang Jiang

Softmax with the cross entropy loss is the standard configuration for current neural classification models. The gold score for a target class is supposed to be 1, but it is never reachable under the softmax schema. Such a problem makes the…

Machine Learning · Computer Science 2025-08-06 Qi Lv , Lei Geng , Ziqiang Cao , Min Cao , Sujian Li , Wenjie Li , Guohong Fu

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

Computation and Language · Computer Science 2020-04-24 Chen Zhu , Yu Cheng , Zhe Gan , Siqi Sun , Tom Goldstein , Jingjing Liu

The combination of pre-trained speech encoders with large language models has enabled the development of speech LLMs that can handle a wide range of spoken language processing tasks. While these models are powerful and flexible, this very…

Computation and Language · Computer Science 2025-05-21 Rao Ma , Mengjie Qian , Vyas Raina , Mark Gales , Kate Knill

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Machine Learning · Computer Science 2019-09-10 Dilin Wang , Chengyue Gong , Qiang Liu

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the…

Computation and Language · Computer Science 2025-10-07 Alex Gibson

Prompt injection is one of the most critical vulnerabilities in LLM agents; yet, effective automated attacks remain largely unexplored from an optimization perspective. Existing methods heavily depend on human red-teamers and hand-crafted…

Machine Learning · Computer Science 2026-02-23 Xin Chen , Jie Zhang , Florian Tramèr

We propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier. We find that only a few manipulations are needed to greatly decrease the accuracy. Our method relies on an atomic flip…

Computation and Language · Computer Science 2018-05-25 Javid Ebrahimi , Anyi Rao , Daniel Lowd , Dejing Dou