相关论文: Detecting Algebraic Manipulation in Leaky Storage …
Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are…
In this paper we present a method which allows attackers to covertly leak data from isolated, air-gapped computers. Our method utilizes the hard disk drive (HDD) activity LED which exists in most of today's desktop PCs, laptops and servers.…
Massive MIMO is one of the salient techniques for achieving high spectral efficiency in next generation wireless networks. Recently, a combined strategy of the massive MIMO and the artificial noise (AN), namely, {\it AN assisted massive…
DNA strands serve as a storage medium for $4$-ary data over the alphabet $\{A,T,G,C\}$. DNA data storage promises formidable information density, long-term durability, and ease of replicability. However, information in this intriguing…
We investigate the problem of maintaining an encoded distributed storage system when some nodes contain adversarial errors. Using the error-correction capabilities that are built into the existing redundancy of the system, we propose a…
AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model (LLM) performance in code generation. We test whether similar…
In [13] we proposed a ({\rho}_r , {\rho}_w )-adversarial wiretap channel model (AWTP) in which the adversary can adaptively choose to see a fraction {\rho}_r of the codeword sent over the channel, and modify a fraction {\rho}_w of the…
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…
We study the information leakage to a guessing adversary in index coding with a general message distribution. Under both vanishing-error and zero-error decoding assumptions, we develop lower and upper bounds on the optimal leakage rate,…
We investigate the role of artificial intelligence in cybersecurity by evaluating how machine learning techniques can detect malicious network activity and identify potential information leakage in cryptographic implementations. We conduct…
The code generation modules inside modern compilers such as GCC and LLVM, which use a limited number of CPU registers to store a large number of program variables, may introduce side-channel leaks even in software equipped with…
Machine learning based malware detection techniques rely on grayscale images of malware and tends to classify malware based on the distribution of textures in graycale images. Albeit the advancement and promising results shown by machine…
We consider an echo-assisted communication model wherein block-coded messages, when transmitted across several frames, reach the destination as multiple noisy copies. We address adversarial attacks on such models wherein a subset of the…
Constrained codes are used to prevent errors from occurring in various data storage and data transmission systems. They can help in increasing the storage density of magnetic storage devices, in managing the lifetime of electronic storage…
Address Space Layout Randomization (ASLR) is one of the most prominently deployed mitigations against memory corruption attacks. ASLR randomly shuffles program virtual addresses to prevent attackers from knowing the location of program…
Modern x86 processors support an AVX instruction set to boost performance. However, this extension may cause security issues. We discovered that there are vulnerable properties in implementing masked load/store instructions. Based on this,…
We address the problem of securing distributed storage systems against eavesdropping and adversarial attacks. An important aspect of these systems is node failures over time, necessitating, thus, a repair mechanism in order to maintain a…
Analogously to classical computers, quantum processors exhibit side channels that may give attackers access to potentially proprietary algorithms. We identify and exploit a previously unexplored side channel in trapped-ion quantum…
Repair operations in distributed storage systems potentially expose the data to malicious acts of passive eavesdroppers or active adversaries, which can be detrimental to the security of the system. This paper presents erasure codes and…
In the inference attacks studied in Quantitative Information Flow (QIF), the adversary typically tries to interfere with the system in the attempt to increase its leakage of secret information. The defender, on the other hand, typically…