Related papers: PoisonBench: Assessing Large Language Model Vulner…

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to…

A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…

Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectively generate…

The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whether the response…

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…

Learned indexes are a class of index data structures that enable fast search by approximating the cumulative distribution function (CDF) using machine learning models (Kraska et al., SIGMOD'18). However, recent studies have shown that…

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive…

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these benchmarks as they may be leaked into pretraining and…

The concept of learned index structures relies on the idea that the input-output functionality of a database index can be viewed as a prediction task and, thus, be implemented using a machine learning model instead of traditional…

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks, which are largely tailored to adult users and neglect the…

Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…

Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy. Nonetheless, FedLLMs remain vulnerable to model poisoning attacks. This article first reviews recent…

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…