Related papers: On the Exploitability of Instruction Tuning
This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, unless specified otherwise, supervised fine-tuning (SFT) and…
In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…
The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…
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…
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a…
Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's dependence on user…
Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a…
Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…
Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…
Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…
Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…
Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs…
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…
Prompting Large Language Models (LLMs), or providing context on the expected model of operation, is an effective way to steer the outputs of such models to satisfy human desiderata after they have been trained. But in rapidly evolving…
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…
Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of…
With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the…
The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…