CAIN: Hijacking LLM-Humans Conversations Via a Two-Stage Malicious System Prompt Generation and Refining Framework

Large language models LLMs have advanced many applications, but are also known to be vulnerable to adversarial attacks. In this work, we introduce a novel security threat: hijacking AI-human conversations by manipulating LLMs' system prompts to produce malicious answers only to specific targeted...

Reliable Disentanglement Multi-View Learning against View Adversarial Attacks

Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. However, in...

Zero-Trust Mobility-Aware Authentication Framework for Secure Vehicular Fog Computing Networks

Vehicular Fog Computing VFC is a promising paradigm to meet the low-latency and high-bandwidth demands of Intelligent Transportation Systems ITS. However, dynamic vehicle mobility and diverse trust boundaries introduce critical security challenges. This paper presents a novel Zero-Trust...

Scalable Defense against In-The-Wild Jailbreaking Attacks with Safety Context Retrieval

Large Language Models LLMs are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety and reliability of LLMs in real-world deployment. While...

Alignment under Pressure: the Case for Informed Adversaries When Evaluating LLM Defenses

Large language models LLMs are rapidly deployed in real-world applications ranging from chatbots to agentic systems. Alignment is one of the main approaches used to defend against attacks such as prompt injection and jailbreaks. Recent defenses report near-zero Attack Success Rates ASR even again...

Destabilizing Power Grid and Energy Market by Cyberattacks on Smart Inverters

Cyberattacks on smart inverters and distributed PV are becoming an imminent threat, because of the recent well-documented vulnerabilities and attack incidents. Particularly, the long lifespan of inverter devices, users' oblivion of cybersecurity compliance, and the lack of cyber regulatory...

Lessons from Defending Gemini against Indirect Prompt Injections

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require access to untrusted data introducing risk. Adversaries can embed malicious instructions in untrusted data which caus...

D4+: Emergent Adversarial Driving Maneuvers with Approximate Functional Optimization

Intelligent mechanisms implemented in autonomous vehicles, such as proactive driving assist and collision alerts, reduce traffic accidents. However, verifying their correct functionality is difficult due to complex interactions with the environment. This problem is exacerbated in adversarial...

CSAGC-IDS: a Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data

As computer networks proliferate, the gravity of network intrusions has escalated, emphasizing the criticality of network intrusion detection systems for safeguarding security. While deep learning models have exhibited promising results in intrusion detection, they face challenges in managing...

Why CTEM is the Winning Bet for CISOs in 2025

Continuous Threat Exposure Management CTEM has moved from concept to cornerstone, solidifying its role as a strategic enabler for CISOs. No longer a theoretical framework, CTEM now anchors today's cybersecurity programs by continuously aligning security efforts with real-world risk. At the heart ...

Recommender Systems for Democracy: toward Adversarial Robustness in Voting Advice Applications

Voting advice applications VAAs help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks these applications pose to the democratic process when targeted by adversarial entities. In particular, we expose 11...

FlowPure: Continuous Normalizing Flows for Adversarial Purification

Despite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has emerged as a promising defense strategy. To achieve...

FABLE: a Localized, Targeted Adversarial Attack on Weather Forecasting Models

Deep learning-based weather forecasting models have recently demonstrated significant performance improvements over gold-standard physics-based simulation tools. However, these models are vulnerable to adversarial attacks, which raises concerns about their trustworthiness. In this paper, we first...

Self-Destructive Language Model

Harmful fine-tuning attacks pose a major threat to the security of large language models LLMs, allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment, they fail to address models' inherent "trainability" on harmfu...

Adversarially Robust Spiking Neural Networks with Sparse Connectivity

Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further ensure the reliability of these systems against malicious actors, recent works have extensively studied adversarial...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...

The Ephemeral Threat: Assessing the Security of Algorithmic Trading Systems Powered by Deep Learning

We study the security of stock price forecasting using Deep Learning DL in computational finance. Despite abundant prior research on the vulnerability of DL to adversarial perturbations, such work has hitherto hardly addressed practical adversarial threat models in the context of DL-powered...

SecReEvalBench: a Multi-Turned Security Resilience Evaluation Benchmark for Large Language Models

The increasing deployment of large language models in security-sensitive domains necessitates rigorous evaluation of their resilience against adversarial prompt-based attacks. While previous benchmarks have focused on security evaluations with limited and predefined attack domains, such as...

Evaluating the Robustness of Adversarial Defenses in Malware Detection Systems

Machine learning is a key tool for Android malware detection, effectively identifying malicious patterns in apps. However, ML-based detectors are vulnerable to evasion attacks, where small, crafted changes bypass detection. Despite progress in adversarial defenses, the lack of comprehensive...

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Large Language Models LLMs are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art...