arXiv:2606. 13952v1 Announce Type: cross Abstract: Active Motor Noise Cancellation (AMNC) ships in commercial fused deposition modeling (FDM) 3D printers as a hardware countermeasure against acoustic side-channel attacks that target intellectual property (IP).
arXiv:2606. 13952v2 Announce Type: replace-cross Abstract: Active Motor Noise Cancellation (AMNC) is a noise-reduction feature shipped in commercial fused deposition modeling (FDM) 3D printers.
arXiv:2610.09819v1 Announce Type: cross Abstract: Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to spea...
The paper introduces BiShield-TEE, a bilateral obfuscation framework for on-device large language models that jointly transforms input and output dimensions to create ambiguous solutions, thereby protecting the model from reverse engineering. It identifies a vulnerability in existing unilateral obfuscation methods—called the Solution Determinacy Property (SDP)—which allows attackers to recover the model’s true key and achieve high attack accuracy. Experiments demonstrate that BiShield-TEE limits attack success to the baseline black‑box level while improving inference efficiency on real hardware.
arXiv:2606. 27701v1 Announce Type: cross Abstract: While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood.
arXiv:2606. 14658v1 Announce Type: cross Abstract: Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras.
Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a target model. Existing MIAs rely on model outputs, r...
The paper introduces PSCMIA, a power side‑channel membership inference attack that can determine whether a data sample was used to train an embedded machine learning model by analyzing power traces, without needing prediction probabilities or labels. The authors evaluate PSCMIA on MNIST, FMNIST, CIFAR10, and CINIC10 datasets using fully connected and convolutional neural networks on STM32F3 and XMEGA platforms, achieving ROC‑AUC values up to 0.907 for fully connected models and close performance to probability‑vector attacks for CNNs. PSCMIA outperforms label‑only attacks in 11 of 16 configurations, showing that physical execution can leak membership information even when conventional outputs are suppressed.
arXiv:2607. 16870v1 Announce Type: cross Abstract: End-to-end speech language models increasingly represent user speech with speech tokens rather than relying exclusively on cascaded ASR--LLM--TTS pipelines.
The paper introduces the Spectral Masking and Interpolation Attack (SMIA), a black‑box adversarial technique that subtly alters inaudible frequency regions of AI‑generated audio to fool voice authentication systems and their countermeasures. Experiments show SMIA achieves at least 82% success against combined verification and countermeasure systems, 97.5% against standalone speaker verification, and 100% against countermeasures, revealing a critical security gap. The authors argue that current static defenses are inadequate and call for dynamic, context‑aware defenses that can adapt to evolving threats.
arXiv:2606. 28649v1 Announce Type: cross Abstract: We present RIPA, the first systematic multi-channel empirical study of prompt injection attacks delivered through the sensory pipeline of a ROS 2-based LLM-controlled robotic system.
arXiv:2606. 05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models.
The paper presents an autoencoder-based acoustic anomaly detection system implemented on Intel’s Loihi 2 neuromorphic processor. It achieves high detection performance—0.9959 AUC on a clean ToyADMOS ToyCar benchmark and 0.7990 source AUC on a noisy DCASE 2026 Task 2 ToyCar benchmark—while operating with only 0.0406–0.0426 mJ of dynamic energy per sample, far below CPU and GPU baselines. The system demonstrates that low‑power, on‑chip inference is feasible for persistent machine monitoring.