arXiv Machine Learning

On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders

The paper investigates the adversarial vulnerability of neural receivers that incorporate unrolled LDPC decoders for 5G NR. It finds that standard gradient-based attacks are ineffective due to gradient masking caused by tanh saturation in the BP check-node update, leading to a dramatic decay in gradient norm over iterations. To overcome this, the authors propose two loss functions—L_BP and L_LLR—that restore attack efficacy, significantly increasing block-error rates across different neural receiver implementations.

arXiv AI

Oct 9

Neural Network Verification for Deep Joint Source-Channel Coding

The paper introduces the first bound‑propagation framework for verifying the decoder of Deep Joint Source‑Channel Coding (DeepJSCC), providing worst‑case reconstruction error guarantees over a specified wireless channel noise region. It extends existing DNN verification techniques to handle PReLU activations, transposed convolutions, and Rayleigh fading, and incorporates Lipschitz‑regularized global robustness training (GloRo) to tighten certification bounds. Experiments on image transmission models show significant improvements in certified safety and real‑world OFDM validation confirms the theoretical guarantees.

By Thanh Le, Hai Duong, Takeshi Matsumura, ThanhVu Nguyen

benchmarks safety

arXiv AI

Jun 18

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration

arXiv:2505. 03646v5 Announce Type: replace-cross Abstract: Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions.

By Chethan Krishnamurthy Ramanaik, Arjun Roy, Tobias Callies, Eirini Ntoutsi

multimodal safety

arXiv Machine Learning

Sep 16

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

arXiv:2609.16204v1 Announce Type: new Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects...

By Aashiq Muhamed, Mona T. Diab, Virginia Smith

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jul 14

AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation

arXiv:2607. 11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances.

By Chenyang Li, Kaige Li, Zeyu Jiang, Changhao Chen

llms agents robotics multimodal safety

arXiv Machine Learning

Aug 12

Masked Neural Detection for Run-Length-Limited Channel Coding in Molecular Communication

arXiv:2606. 12489v2 Announce Type: replace-cross Abstract: Molecular communication (MC) suffers from severe diffusion memory because molecules released for one symbol may arrive during later symbol intervals.

By Melih \c{S}ahin, Ozgur B. Akan

diffusion

arXiv Computer Vision

Sep 18

Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability

The paper introduces Fast Preemptive Robustification (FPR), a lightweight defense that enhances the robustness of deep neural networks against transferable adversarial attacks. By sharpening Laplacian responses through a single 3×3 channel‑wise convolution, FPR eliminates the need for surrogate models, iterative optimization, or specialized training. Experiments show that FPR lowers untargeted attack success rates by 12.7% and reduces targeted attack success from 10.7% to 4.1%.

By Jiaming Liang, Chi-Man Pun

multimodal safety

arXiv AI

Jul 1

Improving Certified Robustness via Adversarial Distillation

arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.

By Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma

efficiency benchmarks safety

arXiv AI

Oct 15

Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion

arXiv:2610.17382v1 Announce Type: cross Abstract: Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft ad...

By Ali Javeri, Javad Hezareh, Radin Shahdaei, AmirMahdi Sadeghzadeh

benchmarks safety

arXiv AI

Jun 2

CEAR: Certified Ensemble Adversarial Robustness in DNNs

arXiv:2606. 01437v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications.

By Daniel Sadig, Mohammadreza Maleki, Hamed Karimi, Reza Samavi

benchmarks safety

arXiv Machine Learning

5d ago

Certified Adaptive List Decoding for Error-Correcting Codes

arXiv:2610.27805v1 Announce Type: cross Abstract: Maximum-likelihood (ML) decoding of linear block codes is NP-hard, so neural decoders are evaluated by how closely they approach it. We observe that...

By Jaeho Hwang, Byung-Sun Won, Uiwon Hwang

diffusion

arXiv Machine Learning

4d ago

LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks

arXiv:2610. 28872v1 Announce Type: new Abstract: The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry about a fifth of the damage a bit flip can do.

By Habibur Rahaman, Swarup Bhunia

llms fine-tuning

Hugging Face Trending Papers

6d ago

Certified Adaptive List Decoding for Error-Correcting Codes

Maximum-likelihood (ML) decoding of linear block codes is NP-hard, so neural decoders are evaluated by how closely they approach it. We observe that proving a candidate optimal can be far easier than...

diffusion

Related stories