Category
1,065 papers
Decoy Direction Optimization (DDO), a fast, post-hoc weight-editing defense that requires no base-model finetuning, is introduced, based on a simple mechanistic insight: ablation attacks rely on contrastive estimators to find the refusal direction.
SWB-DM's cache carries a real warm-up cost, but extending all baselines to the same round budget shows its CIFAR-10 gains are disproportionately large, and on CIFAR-100, FLTrust benefits more -- for reasons entirely unrelated to caching.
API (Application Programming Interface) keys allow applications to authenticate themselves to third-party services. Inadvertent public exposure of these credentials can pose significant consequences, as adversaries can use them to gain privileged access to other services. In this paper, we measure API credential exposu...
Apollo is a social recovery mechanism that aims to avoid any memorability assumptions while strongly protecting recovery metadata privacy, and uses a novel multi-layered secret sharing scheme to mitigate the computational overhead of recovery in this setting, which would otherwise be exponential in the recovery thresho...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces PARSE (Provenance-Aware Retrieval Sanitization), a domain-aware, fact-preserving sanitization pipeline that classifies each sentence by injection likelihood, extracts structured facts before rewriting, and verifies fact preservation via a consistency-checking loop.
This work proposes CiteShade, the first citation laundering attack to RAG, in which an attacker controlling a single source induces a model to produce an attacker-chosen wrong answer and to attribute it to a trusted source that does not support it, while the evidence for the correct answer remains in context.
This work derives Renyi-DP guarantees separating privacy leakage through the posterior mean from a distinct channel induced by the data-dependent posterior covariance, and identifies effective ridge regularisation and covariance scale as the principal privacy-controlling quantities.
As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perception but typically relies on centralized training, where multi-source SAR data are uploaded to a single server, raising privacy and securit...
Machine learning models are increasingly deployed in healthcare imaging pipelines for diagnostic support, and training-time attacks against them are a named sector-level concern: healthcare-sector guidance identifies model poisoning and adversarial attacks as threats requiring dedicated defenses, while federal policy d...
EI-DDLGN is presented, the first in-depth study of TFHE-based DDLGN inference, and how encrypted execution cost depends on model size, learned Boolean-function distribution, and propagated wire status is characterized, and Model-Fixed-Wire PBS Bypass (MFW-PBS Bypass), a semantics-preserving execution strategy that elim...
CanAL, a closed-form water-filling allocation that gives important channels proportionally less noise, is derived and it is proved it strictly minimizes importance-weighted distortion at a fixed budget.
Personal AI agents that run on the user's local machine automate daily tasks including web search, email, and file management. Their access to computer resources, including the network, file system, and shell, exposes them to indirect prompt injection (IPI) attacks. Prior Dual LLM defenses block IPI by replacing untrus...
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.
