Related papers: Algorithmic Complexity Attacks on Dynamic Learned …

Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is…

Deep learning architectures (DLA) have shown impressive performance in computer vision, natural language processing and so on. Many DLA make use of cloud computing to achieve classification due to the high computation and memory…

Decision-based attack poses a severe threat to real-world applications since it regards the target model as a black box and only accesses the hard prediction label. Great efforts have been made recently to decrease the number of queries;…

The growing computational demand for deep neural networks ( DNNs) has raised concerns about their energy consumption and carbon footprint, particularly as the size and complexity of the models continue to increase. To address these…

Classical machine learning algorithms often face scalability bottlenecks when they are applied to large-scale data. Such algorithms were designed to work with small data that is assumed to fit in the memory of one machine. In this report,…

Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially…

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…

Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…

Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in…

We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not require access to the likelihood. This policy, an amortized…

The phenomenon of adversarial examples has been revealed in variant scenarios. Recent studies show that well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples. However,…

Learned indexes leverage machine learning models to accelerate query answering in databases, showing impressive practical performance. However, theoretical understanding of these methods remains incomplete. Existing research suggests that…

Deep learning based intrusion detection systems (DL-based IDS) have emerged as one of the best choices for providing security solutions against various network intrusion attacks. However, due to the emergence and development of adversarial…

An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. While standard AL heuristics, such as selecting those points for annotation for which a…

Algorithmic complexity vulnerabilities are a class of security problems that enables attackers to trigger the worst-case complexity of certain algorithms. Such vulnerabilities can be leveraged to deploy low-volume, asymmetric, CPU-based…

In this paper, we propose exact passive-aggressive (PA) online algorithms for learning to rank. The proposed algorithms can be used even when we have interval labels instead of actual labels for examples. The proposed algorithms solve a…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

Advanced Persistent Threats (APTs) are sophisticated multi-step attacks, planned and executed by skilled adversaries targeting modern government and enterprise networks. Intrusion Detection Systems (IDSs) and User and Entity Behavior…

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…