Smart-grid detector study finds shuffled tests overstate attack detection
Temporal evaluation drops macro-F1 from 0.96 to 0.88, and stealthy false-data injection defeats all three observation views.
Stories per day · 30 days
2 RSS
Relatedarxiv1backdoor1baseband1cognitive-radar1deep-learning1detection1detectors1dnn1electronic-warfare1false-data-injection1gan1graph-learning1iec-1041image-classification1malware-detection1malware-generation1measurement1relational-graphs1
19 stories, newest first · one card per story
Stories tagged #adversarial-ml
Study finds when trusting graph relations hurts detectors
Clean-trained graph detectors fell below graph-free counterparts in 58 of 90 settings on six graphs.
Researchers propose SSTA to deceive cognitive radars across architectures
Authors report a 10.36% higher average black-box success rate and 0 dB main-lobe attenuation after matched filtering.
Mal-AAEGAN generates adversarial malware in a continuous latent space
It matches or beats three binary-space GAN baselines against eight detectors on two API-feature datasets.
Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness
A study finds image-classifier backdoors that look stealthy in one space often leave clear footprints in another.
Don't Let One Lie Survive A Hundred Truths: A Selective Bayesian Trust Estimator for Collaborative Perception
SABER detects stealthy single-object attacks in vehicle collaborative perception while lowering benign false positives.
LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization
LiBRA attack removes AI-image watermarks in an autoencoder's latent space while preserving quality, steering decoder confidence toward random guessing instead of inversion.
Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
Dagger steals GNN models from hard-label APIs with higher fidelity and far fewer queries.
TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers
TrackFlood overloads real-time trackers behind NMS-free detectors, causing deadline misses at higher budgets.
Revisiting Certified Defense with Differential Privacy on Vision Transformers
Laplace PixelDP noise after Vision Transformer patch embeddings collapses accuracy; spectral-norm repair voids the usual certificate.
T-Backdoor: Exploiting Temporal Redundancy in Neuromorphic Data for Spike-preserving Backdoor Attacks on SNNs
T-Backdoor uses purely temporal triggers to backdoor spiking neural networks, reaching about 100% success against seven defenses.
When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers
SpectrumAudit shows many wearable activity models lose accuracy mainly from sensor DC offsets, not temporal signal changes.
RAMP: Reversing Adversarial Perturbations to Strengthen Clean-Label Backdoor Attacks against Malware Detectors
RAMP uses reversed adversarial perturbations to strengthen clean-label backdoors against malware detectors.
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
LoRango pairs two individually benign LoRA adapters so co-loading unlocks hidden malicious behaviors in Stable Diffusion v1.5 and SDXL with ~98% success.
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
Researchers present Micro-Collaborative Poisoning, which splits a false claim across documents to poison RAG systems.
A GAN-Based Framework for Robust DDoS Attack Detection
WGAN-GP-generated adversarial DDoS traffic augments training data, improving detection resilience against evasion attempts.
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
InceptionRAG fragments malicious payloads into dormant passages that trigger LLMs to self-deduce misinformation via multi-hop reasoning, bypassing existing RAG poisoning defenses.
Implementing a White-Box Undetectable Backdoor for Random Fourier Features
Researchers implement Goldwasser's CLWE-based undetectable backdoor for Random Fourier Features models in numpy/scipy, confirming practical realizability with no detectable differences from clean models.
Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness
Researchers model industrial Windows malware detection as a Compound AI System, quantifying trade-offs between detection accuracy, efficiency, and adversarial robustness under tiered attacker knowledge.