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

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…

Due to increasing concerns of data privacy, databases are being encrypted before they are stored on an untrusted server. To enable search operations on the encrypted data, searchable encryption techniques have been proposed. Representative…

Recent cryptanalytic attacks have exposed the vulnerabilities of some widely used cryptographic hash functions like MD5 and SHA-1. Attacks in the line of differential attacks have been used to expose the weaknesses of several other hash…

Scan chains provide increased controllability and observability for testing digital circuits. The increased testability, however, can also be a source of information leakage for sensitive designs. The state-of-the-art defenses to secure…

Here we introduce an improved approach to Variational Quantum Attack Algorithms (VQAA) on crytographic protocols. Our methods provide robust quantum attacks to well-known cryptographic algorithms, more efficiently and with remarkably fewer…

The development of large-scale identification systems that ensure the privacy protection of enrolled subjects represents a major challenge. Biometric deployments that provide interoperability and usability by including efficient…

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving…

Searchable symmetric encryption (SSE) supports keyword search over outsourced symmetrically encrypted data. Dynamic searchable symmetric encryption (DSSE), a variant of SSE, further enables data updating. Most DSSE works with conjunctive…

Sentence-level representations are beneficial for various natural language processing tasks. It is commonly believed that vector representations can capture rich linguistic properties. Currently, large language models (LMs) achieve…

Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient,…

Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive information (e.g. private face images used in training a face…

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.…

This paper describes an advanced SQL injection technique where DNS resolution process is exploited for retrieval of malicious SQL query results. Resulting DNS requests are intercepted by attackers themselves at the controlled remote name…

Side-channel information leakage is a known limitation of SGX. Researchers have demonstrated that secret-dependent information can be extracted from enclave execution through page-fault access patterns. Consequently, various recent research…

Lightweight cryptography is a novel diversion from conventional cryptography that targets internet-of-things (IoT) platform due to resource constraints. In comparison, it offers smaller cryptographic primitives such as shorter key sizes,…

Decision-based attacks (DBA), wherein attackers perturb inputs to spoof learning algorithms by observing solely the output labels, are a type of severe adversarial attacks against Deep Neural Networks (DNNs) requiring minimal knowledge of…

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

Detecting weaknesses in cryptographic algorithms is of utmost importance for designing secure information systems. The state-of-the-art soft analytical side-channel attack (SASCA) uses physical leakage information to make probabilistic…