English
Related papers

Related papers: Can Small-Scale Data Poisoning Exacerbate Dialect-…

200 papers

Large Language Model (LLM) agents relying on external retrieval are increasingly deployed in high-stakes environments. While existing adversarial attacks primarily focus on content falsification or instruction injection, we identify a…

Cryptography and Security · Computer Science 2025-12-17 Xingfu Zhou , Pengfei Wang

Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In this paper, we present Poison-with-Style (PwS), a practical and stealthy model poisoning…

Cryptography and Security · Computer Science 2026-05-28 Khang Tran , Yazan Boshmaf , Issa Khalil , NhatHai Phan , Ting Yu , Md Rizwan Parvez

Despite their wide adoption, the biases and unintended behaviors of language models remain poorly understood. In this paper, we identify and characterize a phenomenon never discussed before, which we call semantic leakage, where models leak…

Computation and Language · Computer Science 2025-05-19 Hila Gonen , Terra Blevins , Alisa Liu , Luke Zettlemoyer , Noah A. Smith

Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these…

Computation and Language · Computer Science 2026-01-22 Chaymaa Abbas , Nour Shamaa , Mariette Awad

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin

Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit tendencies to magnify or reduce biases and potentially…

Computation and Language · Computer Science 2024-11-28 Haniyeh Ehsani Oskouie , Christina Chance , Claire Huang , Margaret Capetz , Elizabeth Eyeson , Majid Sarrafzadeh

Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network models gaining increasing popularity is structured state space…

Machine Learning · Computer Science 2025-12-16 Yonatan Slutzky , Yotam Alexander , Noam Razin , Nadav Cohen

Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional…

Computation and Language · Computer Science 2021-09-28 Matan Halevy , Camille Harris , Amy Bruckman , Diyi Yang , Ayanna Howard

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores…

Computation and Language · Computer Science 2025-05-30 Herun Wan , Minnan Luo , Zhixiong Su , Guang Dai , Xiang Zhao

Language is a deep-rooted means of perpetration of stereotypes and discrimination. Large Language Models (LLMs), now a pervasive technology in our everyday lives, can cause extensive harm when prone to generating toxic responses. The…

Software Engineering · Computer Science 2026-02-06 Simone Corbo , Luca Bancale , Valeria De Gennaro , Livia Lestingi , Vincenzo Scotti , Matteo Camilli

The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…

Machine Learning · Computer Science 2025-11-10 Mathias Lundteigen Mohus , Jingyue Li , Zhirong Yang

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

A limited amount of studies investigates the role of model-agnostic adversarial behavior in toxic content classification. As toxicity classifiers predominantly rely on lexical cues, (deliberately) creative and evolving language-use can be…

Computation and Language · Computer Science 2022-01-19 Chris Emmery , Ákos Kádár , Grzegorz Chrupała , Walter Daelemans

Large language models are trained on vast amounts of internet data, prompting concerns and speculation that they have memorized public benchmarks. Going from speculation to proof of contamination is challenging, as the pretraining data used…

Computation and Language · Computer Science 2023-11-27 Yonatan Oren , Nicole Meister , Niladri Chatterji , Faisal Ladhak , Tatsunori B. Hashimoto

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls…

Computation and Language · Computer Science 2026-01-28 Nay Myat Min , Long H. Pham , Yige Li , Jun Sun

Large language models are increasingly used for creative writing and engagement content, raising safety concerns about the outputs. Therefore, casting humor generation as a testbed, this work evaluates how funniness optimization in modern…

Computation and Language · Computer Science 2025-10-22 Atharvan Dogra , Soumya Suvra Ghosal , Ameet Deshpande , Ashwin Kalyan , Dinesh Manocha

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller