CVE-2025-41689

An unauthenticated remote attacker can get access without password protection to the affected device. This enables the unprotected read-only access to the stored measurement data...

Invitation Is All You Need! Promptware Attacks against LLM-Powered Assistants in Production Are Practical and Dangerous

The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware - maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these applications. While prior research warned about a potential shift in the threat...

Semantic Encryption: Secure and Effective Interaction with Cloud-Based Large Language Models Via Semantic Transformation

The increasing adoption of Cloud-based Large Language Models CLLMs has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often overlook the logical structure of user inputs. This oversig...

Hot-Swap MarkBoard: an Efficient Black-Box Watermarking Approach for Large-Scale Model Distribution

Recently, Deep Learning DL models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property IP risks, as models are distributed on numerous local devices, making them...

EdgeAgentX-DT: Integrating Digital Twins and Generative AI for Resilient Edge Intelligence in Tactical Networks

We introduce EdgeAgentX-DT, an advanced extension of the EdgeAgentX framework that integrates digital twin simulations and generative AI-driven scenario training to significantly enhance edge intelligence in military networks. EdgeAgentX-DT utilizes network digital twins, virtual replicas...

Towards Privacy-Preserving and Personalized Smart Homes Via Tailored Small Language Models

Large Language Models LLMs have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home assistants typically transmit user commands, along with user profiles and home...

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding

Federated recommender system FedRec has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full model and entire weight updates between edge devices and the server, causing significant burdens to devices with limited...

Evaluating Apple Intelligence'S Writing Tools for Privacy against Large Language Model-Based Inference Attacks: Insights from Early Datasets

The misuse of Large Language Models LLMs to infer emotions from text for malicious purposes, known as emotion inference attacks, poses a significant threat to user privacy. In this paper, we investigate the potential of Apple Intelligence's writing tools, integrated across iPhone, iPad, and...

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE

To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things IoT devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference tasks. However, it exposes the private model to two primar...

DNS Query Forgery: a Client-Side Defense against Mobile App Traffic Profiling

Mobile applications continuously generate DNS queries that can reveal sensitive user behavioral patterns even when communications are encrypted. This paper presents a privacy enhancement framework based on query forgery to protect users against profiling attempts that leverage these background...

Google Is Using On-Device AI to Spot Scam Texts and Investment Fraud

Android’s “Scam Detection” protection in Google Messages will now be able to flag even more types of digital fraud...

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-Induced Risks and Vulnerabilities

The growing adoption of Large Language Models LLMs has influenced the development of their lighter counterparts-Small Language Models SLMs-to enable on-device deployment across smartphones and edge devices. These SLMs offer enhanced privacy, reduced latency, server-free functionality, and improve...

Age Verification Using Facial Scans

Discord is testing the feature: "We're currently running tests in select regions to age-gate access to certain spaces or user settings," a spokesperson for Discord said in a statement. "The information shared to power the age verification method is only used for the one-time age verification...

On-Device Watermarking: a Socio-Technical Imperative for Authenticity in the Age of Generative AI

As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are centered around robust watermarking of AI outputs. While...

Google Rolls Out AI Scam Detection for Android to Combat Conversational Fraud

Google has announced the rollout of artificial intelligence AI-powered scam detection features to secure Android device users and their personal information. "These features specifically target conversational scams, which can often appear initially harmless before evolving into harmful situations...

AAT 信息泄露漏洞

AAT is a GPS tracking application by bailuk personal developer. It is used for tracking physical activity with a focus on cycling. An information disclosure vulnerability exists in versions prior to AAT v1.26, which stems from being susceptible to data disclosure from a malicious application...

New Android Banking Malware 'ToxicPanda' Targets Users with Fraudulent Money Transfers

Over 1,500 Android devices have been infected by a new strain of Android banking malware called ToxicPanda that allows threat actors to conduct fraudulent banking transactions. "ToxicPanda's main goal is to initiate money transfers from compromised devices via account takeover ATO using a...

goTenna Pro 安全漏洞

The goTenna Pro is a series of devices from goTenna that can create networks for off-grid communications and situational awareness. A security vulnerability exists in goTenna Pro that stems from an encryption key being stored on the device along with a static IV...

CVE-2024-20464

A vulnerability in the Protocol Independent Multicast PIM feature of Cisco IOS XE Software could allow an unauthenticated, remote attacker to cause a denial of service DoS condition on an affected device. This vulnerability is due to insufficient validation of received IPv4 PIMv2 packets. An...

New Android Banking Trojan BingoMod Steals Money, Wipes Devices

Cybersecurity researchers have uncovered a new Android remote access trojan RAT called BingoMod that not only performs fraudulent money transfers from the compromised devices but also wipes them in an attempt to erase traces of the malware. Italian cybersecurity firm Cleafy, which discovered the...