arXiv Machine Learning
Jun 5
Steering Vectors are an Adversarial Attack Surface
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
Adversarial Robustness of Activation Steering in Large Language Models
arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.
Related stories
arXiv AI
Aug 3
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
arXiv:2607. 28959v1 Announce Type: cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs).
arXiv Machine Learning
Jun 26
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
arXiv AI
Jul 3
Safety Targeted Embedding Exploit via Refinement
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
arXiv Machine Learning
Jul 31
Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models
arXiv:2607. 27386v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement.
arXiv Machine Learning
Jul 13
Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal
arXiv:2607. 08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations.
arXiv AI
Jul 16
UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.
arXiv Machine Learning
Jun 15
Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
arXiv:2605. 05983v2 Announce Type: replace Abstract: Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones.
arXiv Machine Learning
Jun 3
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
arXiv:2606. 02947v1 Announce Type: new Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks.
arXiv Machine Learning
Jun 9
Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
Hugging Face Trending Papers
Jul 2
Safety Targeted Embedding Exploit via Refinement
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
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.