Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-To-Image Diffusion Models

Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapt...

Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning

Industrial control systems ICSs are widely used in industry, and their security and stability are very important. Once the ICS is attacked, it may cause serious damage. Therefore, it is very important to detect anomalies in ICSs. ICS can monitor and manage physical devices remotely using...

PromptSleuth: Detecting Prompt Injection Via Semantic Intent Invariance

Large Language Models LLMs are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection PI, where adversaries manipulate model behavior through crafted inputs. As...

UniAud: a Unified Auditing Framework for High Auditing Power and Utility with One Training Run

Differentially private DP optimization has been widely adopted as a standard approach to provide rigorous privacy guarantees for training datasets. DP auditing verifies whether a model trained with DP optimization satisfies its claimed privacy level by estimating empirical privacy lower bounds...

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

Extended reality XR systems, which consist of virtual reality VR, augmented reality AR, and mixed reality XR, offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task M3T federated foundation model...

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning STL models with personal data. Nevertheless, the paradigm has recently shifted towards multi-task data and multi-task learning MTL, targeting generalist and foundation models that can...

Linux Distros Unpatched Vulnerability : CVE-2024-35991

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Convert spinlock to mutex to lock evl workqueue drainworkqueue cannot be...

arekit (>=0.21.0 <=0.22.1), arenets (>=0.23.0 <=0.23.1) +164 more potentially affected by CVE-2021-37691 via tensorflow-gpu (>=1.10.1 <=2.3.2)

tensorflow-gpu PYPI version =1.10.1, =0.21.0, =0.23.0, =0.9.2, =0.1.0, =0.0.1, =0.1.0, =0.0.1, =1.0.0, =1.0.3 - cctv-analysis =0.0.2 - chatbot-nlu =1.0.0 - classitransformers =0.0.1 and more Source cves: CVE-2021-37691 Source advisory: OSV:GHSA-27QF-JWM8-G7F3...

arekit (>=0.21.0 <=0.22.1), arenets (>=0.23.0 <=0.23.1) +161 more potentially affected by CVE-2021-29562 via tensorflow-gpu (>=1.10.1 <=2.1.1)

tensorflow-gpu PYPI version =1.10.1, =0.21.0, =0.23.0, =0.9.2, =0.1.0, =0.0.1, =0.1.0, =0.0.1, =1.0.0, =1.0.3 - cctv-analysis =0.0.2 - chatbot-nlu =1.0.0 - classitransformers =0.0.1 and more Source cves: CVE-2021-29562 Source advisory: OSV:GHSA-36VM-XW34-X4PJ...