Category
1,065 papers
It is shown that reconstructing fully encrypted $X$ coordinates remains challenging, whereas the \texttt{2X} scheme leaks sufficient information through neighboring coordinates to enable accurate reconstruction, demonstrating that the security of selective coordinate encryption depends strongly on encryption granularit...
The PGM-index (Ferragina and Vinciguerra, VLDB'20) is one of the most practical learned indexes, owing to its theoretical elegance and consistently strong empirical performance. It is built on optimal piecewise linear approximations (PLAs) that minimize the number of segments. In this paper, we ask how sensitive this o...
WeaveMark, a robust and scalable multi-bit LLM watermarking scheme based on coded payload spreading, improves payload capacity through multi-bit-per-token spreading (weaving), improving extraction accuracy through soft-decision error-correcting codes, and preserving text quality through unbiased multilayer reweighting.
This work proposes lightweight multi-secret-key protocols for private average aggregation based on RLWE-based Homomorphic Encryption, which substantially reduces ciphertext expansion and online cost, while preserving practical homomorphic aggregation performance.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work presents the first black-box MIA framework explicitly tailored to TTS models at both the speaker and record levels, and characterize the feasible query space and establish two criteria, scorable extent and memorization elicitation, for evaluating five representative queries.
The Private Computation Space (PCS), a deployed, open-source Machine Learning system to provision and process farmer data securely and improve the worst single-site model accuracy by 22.4% and 9.1%, respectively, while preserving privacy.
This work introduces and formalizes context-inference attacks through a security game and evaluates three settings under decreasing attacker knowledge and increasingly indirect delivery of the context: a known context, an unknown context, and a context the agent retrieves through its own tool calls.
LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term ``linguistic illegibility'' to broadl...
The first systematic study of poisoning-based backdoor attacks on Speech Emotion Recognition systems with a focus on threats enabled by text-to-speech (TTS) generated audio is presented, revealing that TTS technology dramatically lowers the barrier to effective backdoor attacks.
LLM agents can combine individually non-revealing tool returns and disclose a sensitive conclusion, creating Tools Orchestration Privacy Risk (TOP-R). We formalize TOP-R through three conditions: conclusion sensitivity, single-source non-inferability, and compositional inferability. We introduce Library-Grounded Revers...
Results show that LLM-based vulnerability injection is feasible, while exposing key limitations in scalability and diversity, and practical challenges including LLMs' non-determinism and the difficulty of preserving contract semantics are reported.
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds \textit{shared experts} to capture consistently useful representations, fur...
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Students from the MIT Cybersecurity Clinic help local governments and other vulnerable organizations defend against digital threats.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
