相关论文: KRATT: QBF-Assisted Removal and Structural Analysi…

Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation,…

Graph prompt tuning has emerged as a promising paradigm to effectively transfer general graph knowledge from pre-trained models to various downstream tasks, particularly in few-shot contexts. However, its susceptibility to backdoor attacks,…

Evaluating the capabilities and risks of foundation models is paramount, yet current methods demand extensive domain expertise, hindering their scalability as these models rapidly evolve. We introduce SKATE: a novel evaluation framework in…

The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread adoption and success, CoT methods often exhibit instability…

Current algorithms for bounded model checking use SAT methods for checking satisfiability of Boolean formulae. These methods suffer from the potential memory explosion problem. Methods based on the validity of Quantified Boolean Formulae…

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommenders. However, despite their extensive adoption, the…

Fault localization is a practical research topic that helps developers identify code locations that might cause bugs in a program. Most existing fault localization techniques are designed for imperative programs (e.g., C and Java) and rely…

Power side-channel attacks on AES exploit data-dependent physical leakage to recover secret keys, but turning noisy leakage observations into a verified AES-128 key remains a hard combinational search problem. SAT-assisted power…

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

Fault-tolerant logical entangling gates are essential for scalable quantum computing, but are limited by the error rates and overheads of physical two-qubit gates and measurements. To address this limitation, we introduce phantom…

The key innovation of our analytical method, CaRT, lies in establishing a new hierarchical, distributed architecture to guarantee the safety and robustness of a given learning-based motion planning policy. First, in a nominal setting, the…

In this paper, we claim that cyclic obfuscation, when properly implemented, poses exponential complexity on SAT or CycSAT attack. The CycSAT, in order to generate the necessary cycle avoidance clauses, uses a pre-processing step. We show…

Defending aligned Large Language Models (LLMs) against jailbreaking attacks is a challenging problem, with existing approaches requiring multiple requests or even queries to auxiliary LLMs, making them computationally heavy. Instead, we…

The rise of Large Language Models (LLMs) has led to significant applications but also introduced serious security threats, particularly from jailbreak attacks that manipulate output generation. These attacks utilize prompt engineering and…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Current quantization methods for LLMs predominantly rely on block-wise structures to maintain efficiency, often at the cost of representational flexibility. In this work, we demonstrate that element-wise quantization can be made as…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

Recent experimental achievements have demonstrated the potential of neutral atom architectures for fault-tolerant quantum computing. These architectures feature the dynamic rearrangement of atoms during computation, enabling nearly…

Logic locking secures hardware designs in untrusted foundries by incorporating key-driven gates to obscure the original blueprint. While this method safeguards the integrated circuit from malicious alterations during fabrication, its…