Related papers: Compiling symbolic attacks to protocol implementat…

In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…

We present a framework for symbolically executing and model checking higher-order programs with external (open) methods. We focus on the client-library paradigm and in particular we aim to check libraries with respect to any definable…

We present a novel black-box jailbreaking framework that integrates multiple LLM-as-Attacker strategies to deliver highly transferable and effective attacks. The framework is grounded in three key insights from prior jailbreaking research…

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Web applications continue to be a favorite target for hackers due to a combination of wide adoption and rapid deployment cycles, which often lead to the introduction of high impact vulnerabilities. Static analysis tools are important to…

End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record system-level activities as audit logs and provide deep…

We propose a comparative performance evaluation of security protocols. The novelty of our approach lies in the use of a polynomial mathematical model that captures the performance of classes of cryptographic algorithms instead of capturing…

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Validation is a central activity when developing formal specifications. Similarly to coding, a possible validation technique is to define upfront test cases or scenarios that a future specification should satisfy or not. Unfortunately,…

Automated black-box testing of APIs typically relies on interface specifications that define available operations and data schemas, but offer limited or no behavioural semantics. This semantic gap amplifies the test-oracle problem and…

Smart contracts are blockchain-based algorithms that execute when specific criteria are satisfied. They are often used to automate the implementation of an agreement so that all parties may be confident of the conclusion right away, without…

Side-channel attacks, which are capable of breaking secrecy via side-channel information, pose a growing threat to the implementation of cryptographic algorithms. Masking is an effective countermeasure against side-channel attacks by…

This work presents ATLAS, an LLM-driven framework that bridges standardized threat modeling and property-based formal verification for System-on-Chip (SoC) security. Starting from vulnerability knowledge bases such as Common Weakness…

A new logic for verification of security policies is proposed. The logic, HyperLTL, extends linear-time temporal logic (LTL) with connectives for explicit and simultaneous quantification over multiple execution paths, thereby enabling…

A number of important real-world protocols including the Transport Layer Security (TLS) protocol have the ability to negotiate various security-related choices such as the protocol version and the cryptographic algorithms to be used in a…

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

With the increasing number of internet-based resources and applications, the amount of attacks faced by companies has increased significantly in the past years. Likewise, the techniques to test security and emulate attacks need to be…

Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can lead to security vulnerabilities, as speculative instructions…

Automatic security protocol analysis is currently feasible only for small protocols. Since larger protocols quite often are composed of many small protocols, compositional analysis is an attractive, but non-trivial approach. We have…

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…