Related papers: PublicCheck: Public Integrity Verification for Ser…

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…

Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models…

Runtime verification is a lightweight verification technique that complements model checking by analyzing system executions at runtime rather than exploring a complete system model in advance. It is particularly useful for partially…

In order to create user-centric and personalized privacy management tools, the underlying models must account for individual users' privacy expectations, preferences, and their ability to control their information sharing activities.…

Deep learning object detectors often return false positives with very high confidence. Although they optimize generic detection performance, such as mean average precision (mAP), they are not designed for reliability. For a reliable…

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Applying differential privacy at scale requires convenient ways to check that programs computing with sensitive data appropriately preserve privacy. We propose here a fully automated framework for {\em testing} differential privacy,…

Cyber-physical systems (CPSs) are widespread in critical domains, and significant damage can be caused if an attacker is able to modify the code of their programmable logic controllers (PLCs). Unfortunately, traditional techniques for…

Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical…

We introduce CheckNet, a method for secure inference with deep neural networks on untrusted devices. CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted…

Testing has become an indispensable activity of software development, yet writing good and relevant tests remains a quite challenging task. One well-known problem is that it often is impossible or unrealistic to test for every outcome, as…

Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification becomes popular…

Evaluation beyond aggregate performance metrics, e.g. F1-score, is crucial to both establish an appropriate level of trust in machine learning models and identify future model improvements. In this paper we demonstrate CrossCheck, an…

Network protocol fingerprinting is used to identify a protocol implementation by analyzing its input-output behavior. Traditionally, fingerprinting operates under a closed-world assumption, where models of all implementations are assumed to…

Generative AI models have substantially improved the realism of synthetic media, yet their misuse through sophisticated DeepFakes poses significant risks. Despite recent advances in deepfake detection, fairness remains inadequately…

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However,…

Software services play a crucial role in daily life, with automated actions determining access to resources and information. Trusting service providers to perform these actions fairly and accurately is essential, yet challenging for users…

Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked…

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…

Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…