相关论文: Attacks on the Search-RLWE problem with small erro…

The problem of detecting network structures plays a central role in distributed computing. One of the fundamental problems studied in this area is to determine whether for a given graph $H$, the input network contains a subgraph isomorphic…

Recent rank-based attacks have reduced the security of Rainbow below the security requirements set out by NIST by speeding up repeated kernel finding operations using classical mathematics techniques. If quantum algorithms are applied to…

Large Language Models (LLMs) are increasingly used for cybersecurity threat analysis, but their deployment in security-sensitive environments raises trust and safety concerns. With over 21,000 vulnerabilities disclosed in 2025, manual…

Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency,…

Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations. However, some attacks assume full availability of the victim…

This paper presents a reinforcement learning (RL) framework that utilizes Frank-Wolfe policy optimization to solve Coding-Tree-Unit (CTU) bit allocation for Region-of-Interest (ROI) intra-frame coding. Most previous RL-based methods employ…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Machine learning is a popular approach to signatureless malware detection because it can generalize to never-before-seen malware families and polymorphic strains. This has resulted in its practical use for either primary detection engines…

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

This paper studies robust nonparametric regression, in which an adversarial attacker can modify the values of up to $q$ samples from a training dataset of size $N$. Our initial solution is an M-estimator based on Huber loss minimization.…

Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the attacker only has access to the hard-label output (prediction…

Deep learning models are vulnerable to external attacks. In this paper, we propose a Reinforcement Learning (RL) based approach to generate adversarial examples for the pre-trained (target) models. We assume a semi black-box setting where…

We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples are surrounded by correctly labeled ones. We demonstrate how…

Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…

This research focused on enhancing post-incident malware forensic investigation using reinforcement learning RL. We proposed an advanced MDP post incident malware forensics investigation model and framework to expedite post incident…

At SAC 2013, Berger et al. first proposed the Extended Generalized Feistel Networks (EGFN) structure for the design of block ciphers with efficient diffusion. Later, based on the Type-2 EGFN, they instantiated a new lightweight block cipher…

Large-scale quantum computing is a significant threat to classical public-key cryptography. In strong "quantum access" security models, numerous symmetric-key cryptosystems are also vulnerable. We consider classical encryption in a model…

Recent studies have revealed the vulnerability of deep neural networks: A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural network misclassify. This makes it unsafe to apply neural…

In this paper we present new arithmetical and algebraic results following the work of Babindamana and al. on hyperbolas and describe in the new results an approach to attacking a RSA-type modulus based on continued fractions, independent…

Few-shot Learning (FSL) methods are being adopted in settings where data is not abundantly available. This is especially seen in medical domains where the annotations are expensive to obtain. Deep Neural Networks have been shown to be…