Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models

• URL: http://arxiv.org/abs/2410.03955v2
• Date: Sun, 13 Oct 2024 00:48:38 GMT
• Title: Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
• Authors: Gang Li, Wendi Yu, Yao Yao, Wei Tong, Yingbin Liang, Qihang Lin, Tianbao Yang,
• Abstract summary: We study how to develop a pretrained vision-language model (aka the CLIP model) for acquiring new capabilities or improving existing capabilities of image classification. Our experiments on improving vision perception capabilities on autonomous driving and scene recognition datasets demonstrate the efficacy of the proposed approach.
• Score: 75.8161094916476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the real world, a learning-enabled system usually undergoes multiple cycles of model development to enhance the system's ability to handle difficult or emerging tasks. This continual model development process raises a significant issue that the model development for acquiring new or improving existing capabilities may inadvertently lose capabilities of the old model, also known as catastrophic forgetting. Existing continual learning studies focus on mitigating catastrophic forgetting by trading off performance on previous tasks and new tasks to ensure good average performance. However, they are inadequate for many applications especially in safety-critical domains, as failure to strictly preserve the performance of the old model not only introduces safety risks and uncertainties but also imposes substantial expenses in the re-improving and re-validation of existing properties. To address this issue, we introduce model developmental safety as a guarantee of a learning system such that in the model development process the new model should strictly preserve the existing protected capabilities of the old model while improving its performance on target tasks. To ensure the model developmental safety, we present a safety-centric framework by formulating the model developmental safety as data-dependent constraints. Under this framework, we study how to develop a pretrained vision-language model (aka the CLIP model) for acquiring new capabilities or improving existing capabilities of image classification. We propose an efficient constrained optimization algorithm with theoretical guarantee and use its insights to finetune a CLIP model with task-dependent heads for promoting the model developmental safety. Our experiments on improving vision perception capabilities on autonomous driving and scene recognition datasets demonstrate the efficacy of the proposed approach.

Related papers

• Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging [102.16497861225358]
  Adapting general-purpose language models to new skills is currently an expensive process. We investigate the effectiveness of adding new skills to preexisting models by training on the new skills in isolation and later merging with the general model.
  arXiv  Detail & Related papers  (2024-10-16T18:23:50Z)
• Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios [32.16984263644299]
  Large Language Models (LLMs) can generate valuable data for safety measures, but often exhibit distributional biases. We propose a novel framework that integrates active learning with clustering to guide LLM generation. Our results show that the proposed framework produces a more representative set of safety scenarios without requiring prior knowledge of the underlying data distribution.
  arXiv  Detail & Related papers  (2024-10-14T21:48:14Z)
• Learning-based Models for Vulnerability Detection: An Extensive Study [3.1317409221921144]
  We extensively and comprehensively investigate two types of state-of-the-art learning-based approaches. We experimentally demonstrate the priority of sequence-based models and the limited abilities of both graph-based models.
  arXiv  Detail & Related papers  (2024-08-14T13:01:30Z)
• Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions [2.50194939587674]
  We propose a new Model-based RL framework to enable efficient policy learning with unknown dynamics. We introduce and explore a novel method for adding safety constraints for model-based RL during training and policy learning.
  arXiv  Detail & Related papers  (2024-05-25T11:21:12Z)
• Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates [13.911586916369108]
  We show that misclassifications in machine-learning models can affect robustness to adversarial examples. We propose a technique, named robustness-congruent adversarial training, to address this issue. We show that our algorithm and, more generally, learning with non-regression constraints, provides a theoretically-grounded framework to train consistent estimators.
  arXiv  Detail & Related papers  (2024-02-27T10:37:13Z)
• Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models [1.6385815610837167]
  This study investigates two prominent quality aware strategies to combat model drift. The former leverages image quality assessment metrics to meticulously select high-quality training data, improving the model robustness. The latter makes use of learned vectors feature from existing models to guide the selection of future data, aligning it with the model's prior knowledge.
  arXiv  Detail & Related papers  (2024-02-11T18:01:52Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models [103.71308117592963]
  We present an algorithm for training self-destructing models leveraging techniques from meta-learning and adversarial learning. In a small-scale experiment, we show MLAC can largely prevent a BERT-style model from being re-purposed to perform gender identification.
  arXiv  Detail & Related papers  (2022-11-27T21:43:45Z)
• On the model-based stochastic value gradient for continuous reinforcement learning [50.085645237597056]
  We show that simple model-based agents can outperform state-of-the-art model-free agents in terms of both sample-efficiency and final reward. Our findings suggest that model-based policy evaluation deserves closer attention.
  arXiv  Detail & Related papers  (2020-08-28T17:58:29Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

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.