Related papers: Vital: Vulnerability-Oriented Symbolic Execution v…

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either safe or unsafe (robust or not robust). This binary encoding…

We present COBALT-TLA, a neuro-symbolic verification loop that pairs an LLM with TLC, the TLA+ model checker, in an automated REPL. The LLM generates bounded TLA+ specifications; TLC acts as a semantic oracle; structured error traces are…

The security development lifecycle (SDL) is becoming an industry standard. Dynamic symbolic execution (DSE) has enormous amount of applications in computer security (fuzzing, vulnerability discovery, reverse-engineering, etc.). We propose…

Software vulnerabilities have been continually disclosed and documented. An important practice in documenting vulnerabilities is to describe the key vulnerability aspects, such as vulnerability type, root cause, affected product, impact,…

The number of malicious software (malware) is growing out of control. Syntactic signature based detection cannot cope with such growth and manual construction of malware signature databases needs to be replaced by computer learning based…

This paper tackles the problem of designing efficient binary-level verification for a subset of information flow properties encompassing constant-time and secret-erasure. These properties are crucial for cryptographic implementations, but…

The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program…

Low-level programming languages with weak/static type systems, such as C and C++, are vulnerable to errors relating to the misuse of memory at runtime, such as (sub-)object bounds overflows, (re)use-after-free, and type confusion. Such…

Static Application Security Testing (SAST) tools often suffer from high false positive rates, leading to alert fatigue that consumes valuable auditing resources. Recent efforts leveraging Large Language Models (LLMs) as filters offer…

Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines supervise only the final response. To address this, we present…

Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex…

Malware, a persistent cybersecurity threat, increasingly targets interconnected digital systems such as desktop, mobile, and IoT platforms through sophisticated attack vectors. By exploiting these vulnerabilities, attackers compromise the…

Though many deep learning (DL)-based vulnerability detection approaches have been proposed and indeed achieved remarkable performance, they still have limitations in the generalization as well as the practical usage. More precisely,…

Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a…

Vulnerability detection for C/C++ code increasingly relies on heavy representations such as code graphs and deep models, while many practical workflows still benefit from fast and reproducible ranking baselines for human triage. This…

Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years. However, the shroud of opacity surrounding the decision-making process of these detectors makes it difficult for security analysts…

Current machine-learning based software vulnerability detection methods are primarily conducted at the function-level. However, a key limitation of these methods is that they do not indicate the specific lines of code contributing to…

Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively…

Augmenting missing key aspects in Textual Vulnerability Descriptions (TVDs) is crucial for effective vulnerability analysis. For instance, in TVDs, key aspects include Attack Vector, Vulnerability Type, among others. These key aspects help…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…