Related papers: TrojanPuzzle: Covertly Poisoning Code-Suggestion M…
With the extensive use of AI in various fields, the issue of AI security has become more significant. The AI data poisoning attacks will be the most threatening approach against AI security after the adversarial examples. As the continuous…
Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on…
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…
The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning. However, this reliance introduces an unexplored attack surface. This paper introduces Trojan Horse…
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…
As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranking list. They could inject malicious comparisons into the…
Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clients. Existing…
Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…
Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…
Trojan backdoor is a poisoning attack against Neural Network (NN) classifiers in which adversaries try to exploit the (highly desirable) model reuse property to implant Trojans into model parameters for backdoor breaches through a poisoned…
Along with the success of deep neural network (DNN) models, rise the threats to the integrity of these models. A recent threat is the Trojan attack where an attacker interferes with the training pipeline by inserting triggers into some of…
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…
Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential…
Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…
Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…
The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While foundational large language models (LLMs) from OpenAI, Google,…
In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…
Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential…
Forecasting plays a crucial role in modern safety-critical applications, such as space operations. However, the increasing use of deep forecasting models introduces a new security risk of trojan horse attacks, carried out by hiding a…
Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack…