arXiv AI September 2, 2026 By Marco Antonio Corallo, Andrea Agiollo, Mauro Conti, Alberto Giaretta

Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective

The paper investigates whether neuro‑symbolic (NeSy) AI models, which combine neural perception with symbolic reasoning, can mitigate backdoor attacks. It presents a systematic evaluation comparing the NeSy framework DeepProbLog to baseline neural networks across eight backdoor settings and four reasoning tasks. Results indicate that NeSy models are generally more robust than pure neural models, but their resilience depends heavily on how strictly the reasoning process is enforced and its alignment with the attack target.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

safety

arXiv AI

Jun 26

HauntAttack: When Attack Follows Reasoning as a Shadow

arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.

By Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui

safety

Hugging Face Trending Papers

Jul 22

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.

llms fine-tuning efficiency multimodal benchmarks

arXiv AI

Aug 7

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

arXiv:2510. 14538v3 Announce Type: replace Abstract: Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.

By Emanuele Marconato, Samuele Bortolotti, Emile van Krieken, Paolo Morettin, Elena Umili, Antonio Vergari, Efthymia Tsamoura, Andrea Passerini, Stefano Teso

safety

arXiv AI

Jul 23

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.

By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang

llms fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Jul 31

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

arXiv:2507. 05113v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model.

By Binyan Xu, Fan Yang, Xilin Dai, Di Tang, Kehuan Zhang

arXiv Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang

llms multimodal safety

One email a morning, machine-written

Related stories

HauntAttack: When Attack Follows Reasoning as a Shadow

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP