Improving Large Language Model Safety with Contrastive Representation Learning

• URL: http://arxiv.org/abs/2506.11938v1
• Date: Fri, 13 Jun 2025 16:42:09 GMT
• Title: Improving Large Language Model Safety with Contrastive Representation Learning
• Authors: Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin,
• Abstract summary: Large Language Models (LLMs) are powerful tools with profound societal impacts.<n>Their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks.<n>We propose a defense framework that formulates model defense as a contrastive representation learning problem.
• Score: 92.79965952162298
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle to generalize across varying attack types, recent advancements in representation engineering offer promising alternatives. In this work, we propose a defense framework that formulates model defense as a contrastive representation learning (CRL) problem. Our method finetunes a model using a triplet-based loss combined with adversarial hard negative mining to encourage separation between benign and harmful representations. Our experimental results across multiple models demonstrate that our approach outperforms prior representation engineering-based defenses, improving robustness against both input-level and embedding-space attacks without compromising standard performance. Our code is available at https://github.com/samuelsimko/crl-llm-defense

Related papers

• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis [3.795071937009966]
  Adrial attacks can jeopardize the integrity of Machine Learning (ML) models.<n>We propose a framework that detects if an adversarial noise instance is being generated.<n>We evaluate our approach against 8 state-of-the-art attacks, including adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-04T20:25:12Z)
• Reformulation is All You Need: Addressing Malicious Text Features in DNNs [43.978490178352935]
  We propose a unified and adaptive defense framework that is effective against both adversarial and backdoor attacks.<n>Our framework outperforms existing sample-oriented defense baselines across a diverse range of malicious textual features.
  arXiv  Detail & Related papers  (2025-02-02T03:39:43Z)
• Scaling Trends in Language Model Robustness [7.725206196110384]
  We study language model robustness across several classification tasks, model families, and adversarial attacks.<n>We find that in the absence of explicit safety training, larger models are not consistently more robust.<n>We find that while attack scaling outpaces adversarial training across all models studied, larger adversarially trained models might give defense the advantage in the long run.
  arXiv  Detail & Related papers  (2024-07-25T17:26:41Z)
• Defense Against Model Extraction Attacks on Recommender Systems [53.127820987326295]
  We introduce Gradient-based Ranking Optimization (GRO) to defend against model extraction attacks on recommender systems. GRO aims to minimize the loss of the protected target model while maximizing the loss of the attacker's surrogate model. Results show GRO's superior effectiveness in defending against model extraction attacks.
  arXiv  Detail & Related papers  (2023-10-25T03:30:42Z)
• Baseline Defenses for Adversarial Attacks Against Aligned Language Models [109.75753454188705]
  Recent work shows that text moderations can produce jailbreaking prompts that bypass defenses. We look at three types of defenses: detection (perplexity based), input preprocessing (paraphrase and retokenization), and adversarial training. We find that the weakness of existing discretes for text, combined with the relatively high costs of optimization, makes standard adaptive attacks more challenging for LLMs.
  arXiv  Detail & Related papers  (2023-09-01T17:59:44Z)
• "What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models [71.91835408379602]
  adversarial examples have been long considered a real threat to machine learning models. We propose an alternative deployment-based defense paradigm that goes beyond the traditional white-box and black-box threat models.
  arXiv  Detail & Related papers  (2021-02-09T20:07:13Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.