Related papers: The Maestro Attack: Orchestrating Malicious Flows …

This research investigates the impact of Denial of Service (DoS) attacks, specifically Internet Control Message Protocol (ICMP) flood attacks, on Autonomous Driving (AD) systems, focusing on their control modules. Two experimental setups…

Recent optical flow methods are almost exclusively judged in terms of accuracy, while their robustness is often neglected. Although adversarial attacks offer a useful tool to perform such an analysis, current attacks on optical flow methods…

Recent studies have shown that graph neural networks (GNNs) are vulnerable against perturbations due to lack of robustness and can therefore be easily fooled. Currently, most works on attacking GNNs are mainly using gradient information to…

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes…

Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in…

Named Data Networking (NDN) is a prominent realization of the vision of Information-Centric Networking. The NDN architecture adopts name-based routing and location-independent data retrieval. Among other important features, NDN integrates…

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can poison or backdoor the resulting model by uploading malicious…

Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…

Traditional backdoor attacks in federated learning (FL) operate within constrained attack scenarios, as they depend on visible triggers and require physical modifications to the target object, which limits their practicality. To address…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

The SYN flood attack is a common attack strategy on the Internet, which tries to overload services with requests leading to a Denial-of-Service (DoS). Highly asymmetric costs for connection setup - putting the main burden on the attackee -…

The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating…

The wireless ad hoc networks are highly vulnerable to distributed denial of service(DDoS) attacks because of its unique characteristics such as open network architecture, shared wireless medium and stringent resource constraints. These…

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…