Related papers: PrettyCat: Adaptive guarantee-controlled software …
Deep learning methods can be used to produce control policies, but certifying their safety is challenging. The resulting networks are nonlinear and often very large. In response to this challenge, we present OVERT: a sound algorithm for…
Hardware vulnerabilities are generally considered more difficult to fix than software ones because they are persistent after fabrication. Thus, it is crucial to assess the security and fix the vulnerabilities at earlier design phases, such…
Large Language Models (LLMs) are susceptible to jailbreak attacks where malicious prompts are disguised using ciphers and character-level encodings to bypass safety guardrails. While these guardrails often fail to interpret the encoded…
Security provisioning has become the most important design consideration for large-scale Internet of Things (IoT) systems due to their critical roles to support diverse vertical applications by connecting heterogenous devices, machines and…
Classification of personal text messages has many useful applications in surveillance, e-commerce, and mental health care, to name a few. Giving applications access to personal texts can easily lead to (un)intentional privacy violations. We…
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However,…
Satisfiability solvers are increasingly playing a key role in software verification, with particularly effective use in the analysis of security vulnerabilities. String processing is a key part of many software applications, such as…
Artificial Intelligence (AI) advancements have enabled the development of Large Language Models (LLMs) that can perform a variety of tasks with remarkable semantic understanding and accuracy. ChatGPT is one such LLM that has gained…
In this paper, we present a quantum secure multi-party summation protocol, which allows multiple mutually distrustful parties to securely compute the summation of their secret data. In the presented protocol, a semitrusted third party is…
We propose pretty simple password-authenticated key-exchange protocol which is based on the difficulty of solving DDH problem. It has the following advantages: (1) Both $y_1$ and $y_2$ in our protocol are independent and thus they can be…
Many systems today distribute trust across multiple parties such that the system provides certain security properties if a subset of the parties are honest. In the past few years, we have seen an explosion of academic and industrial…
After a general introduction, the thesis is divided into four parts. In the first, we discuss the task of coin tossing, principally in order to highlight the effect different physical theories have on security in a straightforward manner,…
We investigate two-party cryptographic protocols that are secure under assumptions motivated by physics, namely relativistic assumptions (no-signalling) and quantum mechanics. In particular, we discuss the security of bit commitment in…
As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…
Current algorithms for large-scale industrial optimization problems typically face a trade-off: they either require exponential time to reach optimal solutions, or employ problem-specific heuristics. To overcome these limitations, we…
How to achieve differential privacy in the distributed setting, where the dataset is distributed among the distrustful parties, is an important problem. We consider in what condition can a protocol inherit the differential privacy property…
Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from…
We consider the implementation of two-party cryptographic primitives based on the sole assumption that no large-scale reliable quantum storage is available to the cheating party. We construct novel protocols for oblivious transfer and bit…
Distributed linearly separable computation, where a user asks some distributed servers to compute a linearly separable function, was recently formulated by the same authors and aims to alleviate the bottlenecks of stragglers and…
Side-channel attacks impose a serious threat to cryptographic algorithms, including widely employed ones, such as AES and RSA. These attacks take advantage of the algorithm implementation in hardware or software to extract secret…