New research targets AI robustness with novel distillation and testing methods · 8 sources tracked
ByPulseAugur Editorial·[9 sources]·
Researchers are exploring new methods to enhance the adversarial robustness of neural networks. One approach, AD-CERT, combines adversarial distillation with Interval Bound Propagation to achieve state-of-the-art certified performance on robustness benchmarks. Another technique, Activation Amplification and Attenuation (A3), uses a lightweight plug-in module to dynamically rescale activations, improving robustness with minimal overhead. Additionally, studies are investigating the role of input dimensionality, finding that higher dimensions generally make adversarial examples easier to construct and control. Proteus, a framework from Resemble AI, automates adversarial robustness testing for audio deepfake detectors by systematically applying audio transformations.
AI
IMPACT
These advancements in adversarial robustness and testing methodologies are crucial for deploying AI systems more reliably and securely in real-world applications.
RANK_REASON
Multiple arXiv papers presenting novel research in AI robustness and adversarial attacks.
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. For neural netwo…
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. For neural networks, certified training methods based purely on ti…
arXiv cs.AI
TIER_1English(EN)·Nicolas M. M\"uller, Aditya Tirumala Bukkapatnam, Zohaib Ahmed·
arXiv:2606.29544v1 Announce Type: cross Abstract: We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system. Given a detector, Proteus systematically searches over sequences of everyday audio transformations (…
arXiv:2606.27784v1 Announce Type: cross Abstract: The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, or feature recalibration, we instead propose to joi…
The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, or feature recalibration, we instead propose to jointly learn to amplify and attenuate these signals …
arXiv:2406.10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural net…
arXiv cs.LG
TIER_1English(EN)·Matthew J. Colbrook, Igor Mezi\'c, Alexei Stepanenko·
arXiv:2407.06312v2 Announce Type: replace-cross Abstract: Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or generalize, leaving open a central question: When can system behavior be learned …
arXiv:2606.26207v1 Announce Type: new Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, …
Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this…
