Related papers: Security Mitigations for Return-Oriented Programmi…
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…
Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…
We propose in this paper a new propagation vector for malicious software by abusing the Tor network. Tor is particularly relevant, since operating a Tor exit node is easy and involves low costs compared to attack institutional or ISP…
Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…
The implementations of most hardened cryptographic libraries use defensive programming techniques for side-channel resistance. These techniques are usually specified as guidelines to developers on specific code patterns to use or avoid.…
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense mechanisms have made notable progress, they fail to protect…
Consumer and defense systems demanded design and manufacturing of electronics with increased performance, compared to their predecessors. As such systems became ubiquitous in a plethora of domains, their application surface increased, thus…
Distributed Denial of Service (DDoS) attacks exhaust victim's bandwidth or services. Traditional architecture of Internet is vulnerable to DDoS attacks and an ongoing cycle of attack & defense is observed. In this paper, different types and…
Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited embedded platforms…
Adversarial machine learning, focused on studying various attacks and defenses on machine learning (ML) models, is rapidly gaining importance as ML is increasingly being adopted for optimizing wireless systems such as Open Radio Access…
Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…
Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…
Debuggers are a popular reverse engineering and tampering tool. Self-debugging is an effective technique for applications to defend themselves against hostile debuggers. In penetration tests on state-of-the-art self-debugging, we observed…
System auditing is a crucial technique for detecting APT attacks. However, attackers may try to compromise the system auditing frameworks to conceal their malicious activities. In this paper, we present a comprehensive and systematic study…
Side-channel attacks impose a serious threat to cryptographic algorithms, including widely employed ones, such as AES and RSA. These attacks take advantage of the algorithm implementation in hardware or software to extract secret…
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…
Spoofing with falsified IP-MAC pair is the first step in most of the LAN based-attacks. Address Resolution Protocol (ARP) is stateless, which is the main cause that makes spoofing possible. Several network level and host level mechanisms…
This paper introduces a novel approach for the automated selection of software protections to mitigate MATE risks against critical assets within software applications. We formalize the key elements involved in protection decision-making -…
As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…