相关论文: High Recovery with Fewer Injections: Practical Bin…

Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studies the adversarial…

Textual adversarial attacks mislead NLP models, including Large Language Models (LLMs), by subtly modifying text. While effective, existing attacks often require knowledge of the victim model, extensive queries, or access to training data,…

CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…

Large language models (LLMs) possess extensive knowledge and question-answering capabilities, having been widely deployed in privacy-sensitive domains like finance and medical consultation. During LLM inferences, cache-sharing methods are…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to…

We explore an emerging threat model for end-to-end (E2E) encrypted applications: an adversary sends chosen messages to a target client, thereby "injecting" adversarial content into the application state. Such state is subsequently encrypted…

Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency and usually imposing…

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the malware's API call sequences and non-sequential features…

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns…

Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitigate these leakages, they either (1) incur substantial…

We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting, where the adversary only has query access to the top-k ranked unlabeled images from the database.…

Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eavesdropping attacker can effectively recover image data from…

Despite extensive research on cryptography, secure and efficient query processing over outsourced data remains an open challenge. This paper continues along with the emerging trend in secure data processing that recognizes that the entire…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components. The most widely investigated security concern of DNN is from its malicious input, a.k.a…

We propose the Square Attack, a score-based black-box $l_2$- and $l_\infty$-adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. Square Attack is based on a randomized search…