Related papers: Leakage-Abuse Attacks Against Forward and Backward…
We propose to extend the concept of private information retrieval by allowing for distortion in the retrieval process and relaxing the perfect privacy requirement at the same time. In particular, we study the trade-off between download…
Machine Learning (ML) systems are vulnerable to adversarial examples, particularly those from query-based black-box attacks. Despite various efforts to detect and prevent such attacks, ML systems are still at risk, demanding a more…
Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively…
Most TLS clients such as modern web browsers enforce coarse-grained TLS security configurations. They support legacy versions of the protocol that have known design weaknesses, and weak ciphersuites that provide fewer security guarantees…
Searchable encrypted (SE) indexing systems are a useful tool for utilizing cloud services to store and manage sensitive information. However, much of the work on SE systems to date has remained theoretical. In order to make them of…
The growing ubiquity of Retrieval-Augmented Generation (RAG) systems in several real-world services triggers severe concerns about their security. A RAG system improves the generative capabilities of a Large Language Models (LLM) by a…
Forward Secrecy (FS) is a security property in key-exchange algorithms which guarantees that a compromise in the secrecy of a long-term private-key does not compromise the secrecy of past session keys. With a growing awareness of long-term…
Data encryption limits the power and efficiency of queries. Direct processing of encrypted data should ideally be possible to avoid the need for data decryption, processing, and re-encryption. It is vital to keep the data searchable and…
The growing deployment of deep learning models in real-world environments has intensified the need for efficient inference under strict latency and resource constraints. To meet these demands, dynamic deep learning systems (DDLSs) have…
Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms that achieve an optimal trade-off between privacy, utility and…
Distributed Denial of Service (DDoS) attacks persist as significant threats to online services and infrastructure, evolving rapidly in sophistication and eluding traditional detection mechanisms. This evolution demands a comprehensive…
Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct…
This paper investigates the information-theoretic decentralized secure aggregation (DSA) problem under practical groupwise secret keys and collusion resilience. In DSA, $K$ users are interconnected through error-free broadcast channels.…
Organizations use data lakes to store and analyze sensitive data. But hackers may compromise data lake storage to bypass access controls and access sensitive data. To address this, we propose Membrane, a system that (1) cryptographically…
Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as…
Modern processors dynamically control their operating frequency to optimize resource utilization, maximize energy savings, and conform to system-defined constraints. If, during the execution of a software workload, the running average of…
The vigorous development of the Internet has spurred exponential data growth, yet data is predominantly stored in isolated user entities, hampering its full value realization. In large-scale deployment of ``AI+industries'' such as smart…
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct problems and solved separately, since they belong…
Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform…