Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable...

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Representation Engineering typically relies on static refusal vectors derived from terminal representations. We move beyond this paradigm, demonstrating that refusal is a dynamic and sparse process rather than a localized outcome. Using Causal Tracing, we uncover the Refusal Trajectory-a persiste...

PRoADS: Provably Secure and Robust Audio Diffusion Steganography with Latent Optimization and Backward Euler Inversion

This paper proposes PRoADS, a provably secure and robust audio steganographic framework based on audio diffusion models. As a generative steganography scheme, PRoADS embeds secret messages into the initial noise of diffusion models via orthogonal matrix projection. To address the reconstruction...

Robust Provably Secure Image Steganography Via Latent Iterative Optimization

We propose a robust and provably secure image steganography framework based on latent-space iterative optimization. Within this framework, the receiver treats the transmitted image as a fixed reference and iteratively refines a latent variable to minimize the reconstruction error, thereby improvi...

CVE-2026-24892 openITCOCKPIT has Unsafe Deserialization in openITCOCKPIT Changelog Handling

openITCOCKPIT is an open source monitoring tool built for different monitoring engines like Nagios, Naemon and Prometheus. openITCOCKPIT Community Edition 5.3.1 and earlier contains an unsafe PHP deserialization pattern in the processing of changelog entries. Serialized changelog data derived fro...

Influence of Autoencoder Latent Space on Classifying IoT CoAP Attacks

The Internet of Things IoT presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT systems. This study addresses these challenges by explorin...

PenTiDef: Enhancing Privacy and Robustness in Decentralized Federated Intrusion Detection Systems against Poisoning Attacks

The increasing deployment of Federated Learning FL in Intrusion Detection Systems IDS introduces new challenges related to data privacy, centralized coordination, and susceptibility to poisoning attacks. While significant research has focused on protecting traditional FL-IDS with centralized...

Sparse Autoencoders Are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering CC-Delta, an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without...

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Jailbreaking large language models LLMs has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit restricted or unsafe outputs, a phenomenon commonly referred to as...

Kill It with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks

Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a neural network by poisoned training data or a malicious...

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial attack that manipulates audio latent representations to...

Toward Real-World IoT Security: Concept Drift-Resilient IoT Botnet Detection Via Latent Space Representation Learning and Alignment

Although AI-based models have achieved high accuracy in IoT threat detection, their deployment in enterprise environments is constrained by reliance on stationary datasets that fail to reflect the dynamic nature of real-world IoT NetFlow traffic, which is frequently affected by concept drift...

Hybrid Quantum-Classical Autoencoders for Unsupervised Network Intrusion Detection

Unsupervised anomaly-based intrusion detection requires models that can generalize to attack patterns not observed during training. This work presents the first large-scale evaluation of hybrid quantum-classical HQC autoencoders for this task. We construct a unified experimental framework that...

VEIL: Jailbreaking Text-To-Video Models Via Visual Exploitation from Implicit Language

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video T2V models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts...

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models

Recent advances in Large Visual Language Models LVLMs have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security vulnerabilities of LVLMs have become increasingly concerning,...

HYDRA: A Hybrid Heuristic-Guided Deep Representation Architecture for Predicting Latent Zero-Day Vulnerabilities in Patched Functions

Software security testing, particularly when enhanced with deep learning models, has become a powerful approach for improving software quality, enabling faster detection of known flaws in source code. However, many approaches miss post-fix latent vulnerabilities that remain even after patches...

Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

The rapid proliferation of Large Language Models LLMs has raised significant concerns about their security against adversarial attacks. In this work, we propose a novel approach to crafting universal jailbreaks and data extraction attacks by exploiting latent space discontinuities, an architectur...

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix

Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message, whereas most steganalysis methods attempt to detect the embedding in the image space. This paper proposes to perform steganalysis in the latent space by modeling the statistical...

Security-Robustness Trade-Offs in Diffusion Steganography: A Comparative Analysis of Pixel-Space and VAE-Based Architectures

Current generative steganography research mainly pursues computationally expensive mappings to perfect Gaussian priors within single diffusion model architectures. This work introduces an efficient framework based on approximate Gaussian mapping governed by a scale factor calibrated through...

Unmasking Puppeteers: Leveraging Biometric Leakage to Disarm Impersonation in AI-Based Videoconferencing

AI-based talking-head videoconferencing systems reduce bandwidth by sending a compact pose-expression latent and re-synthesizing RGB at the receiver, but this latent can be puppeteered, letting an attacker hijack a victim's likeness in real time. Because every frame is synthetic, deepfake and...