Related papers: CipherGuard: Compiler-aided Mitigation against Cip…

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets…

In this paper, we focus on addressing the challenges of detecting malicious attacks in networks by designing an advanced Explainable Intrusion Detection System (xIDS). The existing machine learning and deep learning approaches have…

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Intelligent software systems powered by Large Language Models (LLMs) are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered…

Host-based cryptomining malware, commonly known as cryptojackers, have gained notoriety for their stealth and the significant financial losses they cause in Linux-based cloud environments. Existing solutions often struggle with scalability…

Chip Guard is a new approach to symbol-correcting error correction codes. It can be scaled to various data burst sizes and reliability levels. A specific version for DDR5 is described. It uses the usual DDR5 configuration of 8 data chips,…

Numerous previous works have studied deep learning algorithms applied in the context of side-channel attacks, which demonstrated the ability to perform successful key recoveries. These studies show that modern cryptographic devices are…

Security of embedded computing systems is becoming of paramount concern as these devices become more ubiquitous, contain personal information and are increasingly used for financial transactions. Security attacks targeting embedded systems…

In this paper we discuss the ability of channel codes to enhance cryptographic secrecy. Toward that end, we present the secrecy metric of degrees of freedom in an attacker's knowledge of the cryptogram, which is similar to equivocation.…

Trusted Execution Environments (TEEs) have emerged as a cornerstone for securing sensitive computations by providing isolated enclaves protected from untrusted software. However, their security guarantees are undermined by vulnerabilities…

Modern microprocessors depend on speculative execution, creating vulnerabilities that enable transient execution attacks. Prior defenses target speculative data leakage but overlook false dependencies from partial address aliasing, where…

In this paper, we consider that, in practice, attack scenarios involving side-channel analysis combine two successive phases:an analysis phase, targeting the extraction of information about the target and the identification of possible…

Developing secure distributed systems is difficult, and even harder when advanced cryptography must be used to achieve security goals. Following prior work, we advocate using secure program partitioning to synthesize cryptographic…

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 models using such defense pipelines, and other frontier…

Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce…

LLM-based code agents(e.g., ChatGPT Codex) are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are believed to provide improved robustness against obfuscated…

We present an instrumenting compiler for enforcing data confidentiality in low-level applications (e.g. those written in C) in the presence of an active adversary. In our approach, the programmer marks secret data by writing lightweight…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

The rapid deployment of Large Language Models (LLMs) has created an urgent need for enhanced security and privacy measures in Machine Learning (ML). LLMs are increasingly being used to process untrusted text inputs and even generate…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…