Related papers: Cute-Lock: Behavioral and Structural Multi-Key Log…

Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to…

Soft real-time applications such as multimedia applications often show bursty memory access patterns---regularly requiring a high memory bandwidth for a short duration of time. Such a period is often critical for timely data processing.…

While reasoning large language models (LLMs) demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where…

Error Detection and Correction Codes (ECCs) are often used in digital designs to protect data integrity. Especially in safety-critical systems such as automotive electronics, ECCs are widely used and the verification of such complex logic…

Lockstep processing is a recognized technique for helping to secure functional-safety relevant processing against, for instance, single upset errors that might cause faulty execution of code. Lockstepping processors does however bind…

Many existing timed-release encryption schemes uses time-lock puzzles to avoid relying on a trusted timeserver or a key holder which could be a weak spot in data security. However, it is unavoidable to consume massive computing power for…

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…

Quantum data locking is a quantum communication primitive that allows the use of a short secret key to encrypt a much longer message. It guarantees information-theoretical security against an adversary with limited quantum memory. Here we…

Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised increasing concerns. Existing research employs red teaming evaluations, utilizing multi-turn…

Quantum data locking is a protocol that allows for a small secret key to (un)lock an exponentially larger amount of information, hence yielding the strongest violation of the classical one-time pad encryption in the quantum setting. This…

Priority queues are abstract data structures which store a set of key/value pairs and allow efficient access to the item with the minimal (maximal) key. Such queues are an important element in various areas of computer science such as…

Numerous threats are associated with the globalized integrated circuit (IC) supply chain, such as piracy, reverse engineering, overproduction, and malicious logic insertion. Many obfuscation approaches have been proposed to mitigate these…

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

This study proposes post-quantum encrypted control systems based on dynamic-key Learning with Errors (LWE) encryption schemes. The proposed method develops update maps that simultaneously update the private key and ciphertexts within the…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

State-of-the-art attacks against cyclic logic obfuscation use satisfiability solvers that are equipped with a set of cycle avoidance clauses. These cycle avoidance clauses are generated in a pre-processing step and define various key…

Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the…

Federated learning (FL) is a promising way to allow multiple data owners (clients) to collaboratively train machine learning models without compromising data privacy. Yet, existing FL solutions usually rely on a centralized aggregator for…

Logic Programming (LP) is a subcategory of declarative programming that is considered to be relatively simple for non-programmers. LP developers focus on describing facts and rules of a logical derivation, and do not need to think about the…