Related papers: Do You Even Lift? Strengthening Compiler Security …

Classes on compiler technology are commonly found in Computer Science curricula, covering aspects of parsing, semantic analysis, intermediate transformations and target code generation. This paper reports on introducing certified…

Parser combinators are a well-known mechanism used for the compositional construction of parsers, and have shown to be particularly useful in writing parsers for rich grammars with data-dependencies and global state. Verifying applications…

We map the space of soundness criteria for secure compilation based on the preservation of hyperproperties in arbitrary adversarial contexts, which we call robust hyperproperty preservation. For this, we study the preservation of several…

RISC-V is gaining popularity for its adaptability and cost-effectiveness in processor design. With the increasing adoption of RISC-V, the importance of implementing robust security verification has grown significantly. In the state of the…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Symbolic execution is an effective path oriented and constraint based program analysis technique. Recently, there is a significant development in the research and application of symbolic execution. However, symbolic execution still suffers…

We present Security Relaxed Separation Logic (SecRSL), a separation logic for proving information-flow security of C11 programs in the Release-Acquire fragment with relaxed accesses. SecRSL is the first security logic that (1) supports…

Universal Composability (UC) is the gold standard for cryptographic security, but mechanizing proofs of UC is notoriously difficult. A recently-discovered connection between UC and Robust Compilation (RC)$\unicode{x2014}$a novel theory of…

We present CureSpec, the first model-checking based framework for automatic repair of programs with respect to information leaks in the presence of side-channels and speculative execution. CureSpec is based on formal models of attacker…

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become…

The outsourced manufacturing of integrated circuits has increased the risk of intellectual property theft. In response, logic locking techniques have been developed for protecting designs by adding programmable elements to the circuit.…

Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initialization vectors or…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Uncertainty, error, and similar complications add to the many challenges of cyber security. Various disciplines have developed methods for managing these complications, but applying these methods involves disambiguating overlapping…

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…

As large language models (LLMs) continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and…

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…