Related papers: PoisonForge: Task-Level Targeted Poisoning Benchma…

With the introduction of the transformers architecture, LLMs have revolutionized the NLP field with ever more powerful models. Nevertheless, their development came up with several challenges. The exponential growth in computational power…

Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced…

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating,…

Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…

Large language model (LLM) benchmarks inform LLM use decisions (e.g., "is this LLM safe to deploy for my use case and context?"). However, benchmarks may be rendered unreliable by various failure modes that impact benchmark bias, variance,…

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…

Poisoning attacks compromise the training phase of federated learning (FL) such that the learned global model misclassifies attacker-chosen inputs called target inputs. Existing defenses mainly focus on protecting the training phase of FL…

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

The growing reliance of intelligent systems on data makes the systems vulnerable to data poisoning attacks. Such attacks could compromise machine learning or deep learning models by disrupting the input data. Previous studies on data…

Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised learning (SSL), which…

Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated superior…

Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that regularization…

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download weights of models pre-trained on large datasets, then fine-tune the weights on a task of their choice. This raises the question of whether downloading…