BadLingual: a Novel Lingual-Backdoor Attack against Large Language Models

In this paper, we present a new form of backdoor attack against Large Language Models LLMs: lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected LLMs to generate inflammatory speech. They enable the precise...

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures

As large language models LLMs continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and categorize the various attacks targeting LLMs, distinguishing...

Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems

This study examines vulnerabilities in transformer-based automated short-answer grading systems used in medical education, with a focus on how these systems can be manipulated through adversarial gaming strategies. Our research identifies three main types of gaming strategies that exploit the...

The vulnerability of the mod_data module in the virtual training environment Moodle, which allows a intruder to gain unauthorized access to protected information

The vulnerability of the moddata module in the virtual training environment Moodle is related to the disclosure of information through query strings. Exploiting this vulnerability could allow an attacker, operating remotely, to gain unauthorized access to protected information...

BadMoE: Backdooring Mixture-Of-Experts LLMs Via Optimizing Routing Triggers and Infecting Dormant Experts

Mixture-of-Experts MoE have emerged as a powerful architecture for large language models LLMs, enabling efficient scaling of model capacity while maintaining manageable computational costs. The key advantage lies in their ability to route different tokens to different "expert'' networks within th...

Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection

According to the Open Web Application Security Project OWASP, Cross-Site Scripting XSS is a critical security vulnerability. Despite decades of research, XSS remains among the top 10 security vulnerabilities. Researchers have proposed various techniques to protect systems from XSS attacks, with...

The Dark Side of Digital Twins: Adversarial Attacks on AI-Driven Water Forecasting

Digital twins DTs are improving water distribution systems by using real-time data, analytics, and prediction models to optimize operations. This paper presents a DT platform designed for a Spanish water supply network, utilizing Long Short-Term Memory LSTM networks to predict water consumption...

JailbreaksOverTime: Detecting Jailbreak Attacks under Distribution Shift

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback RLHF 32, language models remain vulnerable to jailbreak attacks that bypass safety guardrails. Universal jailbreaks - prefixes that can circumvent alignment fo...

Optimized Approaches to Malware Detection: a Study of Machine Learning and Deep Learning Techniques

Digital systems find it challenging to keep up with cybersecurity threats. The daily emergence of more than 560,000 new malware strains poses significant hazards to the digital ecosystem. The traditional malware detection methods fail to operate properly and yield high false positive rates with l...

Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations

This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance...

AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

Enhancing Variational Autoencoders with Smooth Robust Latent Encoding

Variational Autoencoders VAEs have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain largely underexplored. Although adversarial training has been an established technique for enhancing robustness in predicti...

CVE-2020-36845

The KnowBe4 Security Awareness Training application before 2020-01-10 contains a redirect function that does not validate the destination URL before redirecting. The response has a SCRIPT element that sets window.location.href to an arbitrary https URL...

CVE-2020-36845

The KnowBe4 Security Awareness Training application before 2020-01-10 contains a redirect function that does not validate the destination URL before redirecting. The response has a SCRIPT element that sets window.location.href to an arbitrary https URL...

CVE-2020-36844

The KnowBe4 Security Awareness Training application before 2020-01-10 allows reflected XSS. The response has a SCRIPT element that sets window.location.href to a JavaScript URL...

CVE-2020-36844

The KnowBe4 Security Awareness Training application before 2020-01-10 allows reflected XSS. The response has a SCRIPT element that sets window.location.href to a JavaScript URL...

CVE-2020-36845

The KnowBe4 Security Awareness Training application before 2020-01-10 contains a redirect function that does not validate the destination URL before redirecting. The response has a SCRIPT element that sets window.location.href to an arbitrary https URL...

PT-2025-17416 · Knowbe4 · Knowbe4 Security Awareness Training

Name of the Vulnerable Software and Affected Versions: KnowBe4 Security Awareness Training versions prior to 2020-01-10 Description: The issue concerns a redirect function in the application that fails to validate the destination URL before redirecting. This allows the response to contain a SCRIP...

CVE-2020-36844

The KnowBe4 Security Awareness Training application before 2020-01-10 allows reflected XSS. The response has a SCRIPT element that sets window.location.href to a JavaScript URL...

PT-2025-17417 · Knowbe4 · Knowbe4 Security Awareness Training

Name of the Vulnerable Software and Affected Versions: KnowBe4 Security Awareness Training versions prior to 2020-01-10 Description: The issue allows reflected XSS. The response has a SCRIPT element that sets window.location.href to a JavaScript URL. Recommendations: For versions prior to...