相关论文: Countering Trusting Trust through Diverse Double-C…

Recently, Haider et al. introduced the first rigorous hardware Trojan detection algorithm called HaTCh. The foundation of HaTCh is a formal framework of hardware Trojan design, which formally characterizes all the hardware Trojans based on…

Data Poisoning (DP) is an effective attack that causes trained classifiers to misclassify their inputs. DP attacks significantly degrade a classifier's accuracy by covertly injecting attack samples into the training set. Broadly applicable…

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel…

We propose a new formal criterion for secure compilation, providing strong security guarantees for components written in unsafe, low-level languages with C-style undefined behavior. Our criterion goes beyond recent proposals, which protect…

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

Random beacons-information sources that broadcast a stream of random digits unknown by anyone beforehand-are useful for various cryptographic purposes. But such beacons can be easily and undetectably sabotaged, so that their output is known…

Digital twins have recently gained significant interest in simulation, optimization, and predictive maintenance of Industrial Control Systems (ICS). Recent studies discuss the possibility of using digital twins for intrusion detection in…

Computer-based systems have solved several domain problems, including industrial, military, education, and wearable. Nevertheless, such arrangements need high-quality software to guarantee security and safety as both are mandatory for…

Blockchain and distributed ledger technologies (DLTs) facilitate decentralized computations across trust boundaries. However, ensuring complex computations with low gas fees and confidentiality remains challenging. Recent advances in…

Mutation analysis is an effective technique to evaluate a test suite adequacy in terms of revealing unforeseen bugs in software. Traditional source- or IR-level mutation analysis is not applicable to the software only available in binary…

Testing-based methodologies like fuzzing are able to analyze complex software which is not amenable to traditional formal approaches like verification, model checking, and abstract interpretation. Despite enormous success at exposing…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Metamorphic testing is a widely used methodology that examines an expected relation between pairs of executions to automatically find bugs, such as correctness bugs. We found that code coverage cannot accurately measure the extent to which…

Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether…

We explore an approach to verification of programs via program transformation applied to an interpreter of a programming language. A specialization technique known as Turchin's supercompilation is used to specialize some interpreters with…

We propose an efficient framework for enabling secure multi-party numerical computations in a Peer-to-Peer network. This problem arises in a range of applications such as collaborative filtering, distributed computation of trust and…

Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return messages. We show that this convenience creates a…

In this work, we present novel protocols over rings for semi-honest secure three-party computation (3PC) and malicious four-party computation (4PC) with one corruption. While most existing works focus on improving total communication…

Binary code authorship identification determines authors of a binary program. Existing techniques have used supervised machine learning for this task. In this paper, we look this problem from an attacker's perspective. We aim to modify a…

Whenever a bug occurs in a program, software developers assume that the code is flawed, not the compiler. In fact, if compilers should be correct, they are just normal software with their own bugs. Hard to find, errors in them have…