Related papers: TLGLock: A New Approach in Logic Locking Using Key…

Security critical software, e.g., OpenSSL, comes with numerous side-channel leakages left unpatched due to a lack of resources or experts. The situation will only worsen as the pace of code development accelerates, with developers relying…

Large Language Models (LLMs) deliver exceptional performance across natural language tasks but demand substantial computational resources, limiting their deployment on resource-constrained edge devices. Existing compression techniques, such…

Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when…

We study challenges using reinforcement learning in controlling energy systems, where apart from performance requirements, one has additional safety requirements such as avoiding blackouts. We detail how these safety requirements in…

Fine-tuning the large language models (LLMs) are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning (FL)…

In recent years reversible logic has been considered as an important issue for designing low power digital circuits. It has voluminous applications in the present rising nanotechnology such as DNA computing, Quantum Computing, low power…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

Quantum circuits of arithmetic operations such as addition are needed to implement quantum algorithms in hardware. Quantum circuits based on Clifford+T gates are used as they can be made tolerant to noise. The tradeoff of gaining fault…

As sensor nodes are deployed anywhere in a wireless sensor network, hence their communication can be easily monitored. In these networks, message protection and node identification are very issues. Hence, security of large scale such…

Time-Lock Puzzles (TLPs) enable a client to lock a message such that a server can unlock it only after a specified time. They have diverse applications, such as scheduled payments, secret sharing, and zero-knowledge proofs. In this work, we…

Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In…

In the recent past, we have witnessed the shift towards attacks on the microarchitectural CPU level. In particular, cache side-channels play a predominant role as they allow an attacker to exfiltrate secret information by exploiting the CPU…

A long-standing goal of computer technology is to process and store digital information with the same device in order to implement new architectures. One way to accomplish this is to use nanomagnetic `non-volatile' logic gates that can…

Signal Temporal Logic (STL) offers a concise yet expressive framework for specifying and reasoning about spatio-temporal behaviors of robotic systems. Attractively, STL admits the notion of robustness, the degree to which an input signal…

Hardware intellectual property (IP) theft is a major issue in today's globalized supply chain. To address it, numerous logic locking and obfuscation techniques have been proposed. While locking initially focused on digital integrated…

In the quest for novel, scalable and energy-efficient computing technologies, many non-charge based logic devices are being explored. Recent advances in multi-ferroic materials have paved the way for electric field induced low energy and…

Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with…

Although the integration of large language models (LLMs) into robotics has unlocked transformative capabilities, it has also introduced significant safety concerns, ranging from average-case LLM errors (e.g., hallucinations) to adversarial…

In quantum computing, quantum circuits are fundamental representations of quantum algorithms, which are compiled into executable functions for quantum solutions. Quantum compilers transform algorithmic quantum circuits into one compatible…

Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and…