Machine Learning with Privacy for Protected Attributes

Differential privacy DP has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use cases can result in unnecessary degradation of utility. In...

KnowML: Improving Generalization of ML-NIDS with Attack Knowledge Graphs

Despite extensive research on Machine Learning-based Network Intrusion Detection Systems ML-NIDS, their capability to detect diverse attack variants remains uncertain. Prior studies have largely relied on homogeneous datasets, which artificially inflate performance scores and offer a false sense ...

Sapido多款产品 操作系统命令注入漏洞

Sapido BR270n and others are products of Sapido Inc.Sapido BR270n is a wireless router.Sapido BR071n is a router.Sapido BR261c is a router. An operating system command injection vulnerability exists in several Sapido products.The vulnerability stems from OS command injection and could lead to the...

Advantech多款产品 安全漏洞

The Advantech WISE-4010LAN, WISE-4050LAN, and WISE-4060LAN are all industrial automation controllers from Advantech of Taiwan, China. A denial of service vulnerability exists in multiple Advantech products, which can be exploited by attackers to cause a denial of service...

Echo Chamber Jailbreak Tricks LLMs Like OpenAI and Google into Generating Harmful Content

Cybersecurity researchers are calling attention to a new jailbreaking method called Echo Chamber that could be leveraged to trick popular large language models LLMs into generating undesirable responses, irrespective of the safeguards put in place. "Unlike traditional jailbreaks that rely on...

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence AI systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections,...

DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?

Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networks, especially in security-sensitive domains. Evasion attacks, a form of adversarial attack where input is modified a...

VideoMark: a Distortion-Free Robust Watermarking Framework for Video Diffusion Models

Whitepaper called VideoMark: A Distortion-Free Robust Watermarking Framework For Video Diffusion Models...

UCD: Unlearning in LLMs Via Contrastive Decoding

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models LLMs while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive decoding, leveraging two auxiliary smaller models, one train...

VulStamp: Vulnerability Assessment Using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess...

A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis

Foundation models have gained growing interest in the IoT domain due to their reduced reliance on labeled data and strong generalizability across tasks, which address key limitations of traditional machine learning approaches. However, most existing foundation model based methods are developed fo...

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...

Shrinking the Generation-Verification Gap with Weak Verifiers

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable e.g., humans or limited in utility e.g., tools like Lean. While LM judges and reward models have become broadly useful as...

SmartHome-Bench: a Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models

Video anomaly detection VAD is essential for enhancing safety and security by identifying unusual events across different environments. Existing VAD benchmarks, however, are primarily designed for general-purpose scenarios, neglecting the specific characteristics of smart home applications. To...

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Large Language Models LLMs have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or...

Risks and Benefits of LLMs and GenAI for Platform Integrity, Healthcare Diagnostics, Cybersecurity, Privacy and AI Safety: a Comprehensive Survey, Roadmap and Implementation Blueprint

Large Language Models LLMs and generative AI GenAI systems such as ChatGPT, Claude, Gemini, LLaMA, and Copilot, developed by OpenAI, Anthropic, Google, Meta, and Microsoft are reshaping digital platforms and app ecosystems while introducing key challenges in cybersecurity, privacy, and platform...

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models

Vision-Language Models VLMs such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable to adversarial attacks, particularly in the image modality,...

Differential Privacy in Machine Learning: from Symbolic AI to LLMs

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorith...

Smart Buildings Energy Consumption Forecasting Using Adaptive Evolutionary Ensemble Learning Models

Smart buildings are gaining popularity because they can enhance energy efficiency, lower costs, improve security, and provide a more comfortable and convenient environment for building occupants. A considerable portion of the global energy supply is consumed in the building sector and plays a...

Exploring the Secondary Risks of Large Language Models

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less attention has been given to non-adversarial failures that...