Related papers: Message Recovery Attack in NTRU through VFK Lattic…

Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors.…

Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack…

As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Fault-tolerant routing (FTR) in Networks-on-Chip (NoCs) has become a common practice to sustain the performance of multi-core systems with an increasing number of faults on a chip. On the other hand, usage of third-party intellectual…

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

This paper considers a network where a node wishes to transmit a source message to a legitimate receiver in the presence of an eavesdropper. The transmitter secures its transmissions employing a sparse implementation of Random Linear…

This paper presents a general strategy to recover a block cipher secret key in the cold boot attack setting. More precisely, we propose a key-recovery method that combines key enumeration algorithms and Grover's quantum algorithm to recover…

We propose a general framework for reconstructing and denoising single entries of incomplete and noisy entries. We describe: effective algorithms for deciding if and entry can be reconstructed and, if so, for reconstructing and denoising…

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

The Worldvolume Hybrid Monte Carlo method (WV-HMC method) [arXiv:2012.08468] is a reliable and versatile algorithm towards solving the sign problem. Similarly to the tempered Lefschetz thimble method, this method removes the ergodicity…

This paper is devoted to proposing a general weighted low-rank recovery model and designing a fast SVD-free computational scheme to solve it. First, our generic weighted low-rank recovery model unifies several existing approaches in the…

We address the multi-user quantum key distribution (QKD) problem under malicious quantum attacks, which is critical for realizing a large-scale quantum Internet. This paper maximizes the sum secret key rate (SKR) of a novel uplink…

We address the problem of Reliable Broadcast in asynchronous message-passing systems with $n$ nodes, of which up to $t$ are malicious (faulty), in addition to a message adversary that can drop some of the messages sent by correct…

In this paper, we propose a Zero-Touch, deep reinforcement learning (DRL)-based Proactive Failure Recovery framework called ZT-PFR for stateful network function virtualization (NFV)-enabled networks. To this end, we formulate a…

This study presents a hybrid deep learning framework, the Vision Transformer with Residual Feature Network (VRF-Net), for recovering high-resolution system matrices in Magnetic Particle Imaging (MPI). MPI resolution often suffers from…

In this work, we exhibit a hierarchy of polynomial time algorithms solving approximate variants of the Closest Vector Problem (CVP). Our first contribution is a heuristic algorithm achieving the same distance tradeoff as HSVP algorithms,…

Over the last years, threat intelligence sharing has steadily grown, leading cybersecurity professionals to access increasingly larger amounts of heterogeneous data. Among those, cyber attacks' Tactics, Techniques and Procedures (TTPs) have…

Threat analysts routinely rely on natural-language reports that describe attacker actions without enumerating the full kill chain or the dependencies between phases, making automated reconstruction of ATT&CK consistent intrusion paths a…

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…