Related papers: SIP Shaker: Software Integrity Protection Composit…
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of…
We take a divide and conquer approach to design controllers for reachability problems given large-scale linear systems with polyhedral constraints on states, controls, and disturbances. Such systems are made of small subsystems with coupled…
We propose a supervised learning framework for computing solutions of multi-parametric Mixed Integer Linear Programs (MILPs) that arise in Model Predictive Control. Our approach also quantifies sub-optimality for the computed solutions.…
A frustratingly easy technique known as the prefilling attack has been shown to effectively circumvent the safety alignment of frontier LLMs by simply prefilling the assistant response with an affirmative prefix before decoding. In…
In this paper, we propose an algorithm that targets contamination and eavesdropping adversaries. We consider the case when the number of independent packets available to the eavesdropper is less than the multicast capacity of the network.…
Integrated Circuits (ICs) are the target of diverse attacks during their lifetime. Fabrication-time attacks, such as the insertion of Hardware Trojans, can give an adversary access to privileged data and/or the means to corrupt the IC's…
Large Language Models (LLMs) represent valuable intellectual property (IP), reflecting significant investments in training data, compute, and expertise. Deploying these models on partially trusted or insecure devices introduces substantial…
Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…
Integer overflows in commodity software are a main source for software bugs, which can result in exploitable memory corruption vulnerabilities and may eventually contribute to powerful software based exploits, i.e., code reuse attacks…
Quantitative Information Flow (QIF) provides a robust information-theoretical framework for designing secure systems with minimal information leakage. While previous research has addressed the design of such systems under hard constraints…
Self-synchronization under the presence of additive noise can be achieved by allocating a certain number of bits of each codeword as markers for synchronization. Difference systems of sets are combinatorial designs which specify the…
Secure compilers generate compiled code that withstands many target-level attacks such as alteration of control flow, data leaks or memory corruption. Many existing secure compilers are proven to be fully abstract, meaning that they reflect…
In the context of security protocol parallel composition, where messages belonging to different protocols can intersect each other, we introduce a new paradigm: term-based composition (i.e. the composition of message components also known…
The broad landscape of new applications requires minimal hardware resources without any sacrifice in Quality-of-Results. Approximate Computing (AC) has emerged to meet the demands of data-rich applications. Although AC applies techniques to…
Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…
Vulnerabilities emanating from DRAM errors pose a vexing problem that remains, as of yet, unsolved and elusive but cannot be ignored. Prior defenses focused on specific details of early RowHammer attacks and fail to generalize with the…
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or…
Machine learning malware detectors are vulnerable to adversarial EXEmples, i.e., carefully-crafted Windows programs tailored to evade detection. Unlike other adversarial problems, attacks in this context must be functionality-preserving, a…
software component misuse a privileged relationship with the hardware to by pass system protections, monitors, or forensic tools. These relationships are often not illegal and exist between system components by design. Hence, even a system…
We introduce a novel approach to secure compilation based on maps of distributive laws. We demonstrate through four examples that the coherence criterion for maps of distributive laws can potentially be a viable alternative for compiler…