Handing Wang

Xiaobin Li, Kai Wu, Xiaoyu Zhang et al.

The core challenge of high-dimensional and expensive black-box optimization (BBO) is how to obtain better performance faster with little function evaluation cost. The essence of the problem is how to design an efficient optimization strategy tailored to the target task. This paper designs a powerful optimization framework to automatically learn the optimization strategies from the target or cheap surrogate task without human intervention. However, current methods are weak for this due to poor representation of optimization strategy. To achieve this, 1) drawing on the mechanism of genetic algorithm, we propose a deep neural network framework called B2Opt, which has a stronger representation of optimization strategies based on survival of the fittest; 2) B2Opt can utilize the cheap surrogate functions of the target task to guide the design of the efficient optimization strategies. Compared to the state-of-the-art BBO baselines, B2Opt can achieve multiple orders of magnitude performance improvement with less function evaluation cost. We validate our proposal on high-dimensional synthetic functions and two real-world applications. We also find that deep B2Opt performs better than shallow ones.

Zhaoxin Wang, Handing Wang, Cong Tian et al.

Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT methods, fast AT (FAT), which employs a single-step attack strategy to guide the training process, can achieve good robustness against adversarial attacks at a low cost. However, FAT methods suffer from the catastrophic overfitting problem, especially on complex tasks or with large-parameter models. In this work, we propose a FAT method termed FGSM-PCO, which mitigates catastrophic overfitting by averting the collapse of the inner optimization problem in the bi-level optimization process. FGSM-PCO generates current-stage AEs from the historical AEs and incorporates them into the training process using an adaptive mechanism. This mechanism determines an appropriate fusion ratio according to the performance of the AEs on the training model. Coupled with a loss function tailored to the training framework, FGSM-PCO can alleviate catastrophic overfitting and help the recovery of an overfitted model to effective training. We evaluate our algorithm across three models and three datasets to validate its effectiveness. Comparative empirical studies against other FAT algorithms demonstrate that our proposed method effectively addresses unresolved overfitting issues in existing algorithms.

Yudong Yang, Kai Wu, Xiangyi Teng et al.

The field of evolutionary many-task optimization (EMaTO) is increasingly recognized for its ability to streamline the resolution of optimization challenges with repetitive characteristics, thereby conserving computational resources. This paper tackles the challenge of crafting efficient knowledge transfer mechanisms within EMaTO, a task complicated by the computational demands of individual task evaluations. We introduce a novel framework that employs a complex network to comprehensively analyze the dynamics of knowledge transfer between tasks within EMaTO. By extracting and scrutinizing the knowledge transfer network from existing EMaTO algorithms, we evaluate the influence of network modifications on overall algorithmic efficacy. Our findings indicate that these networks are diverse, displaying community-structured directed graph characteristics, with their network density adapting to different task sets. This research underscores the viability of integrating complex network concepts into EMaTO to refine knowledge transfer processes, paving the way for future advancements in the domain.

Jiangtao Liu, Zhaoxin Wang, Handing Wang et al.

Recent advancements in Text-to-Image (T2I) generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt checkers and post-hoc image checkers, are vulnerable to sophisticated adversarial attacks. In this work, we propose TCBS-Attack, a novel query-based black-box jailbreak attack that searches for tokens located near the decision boundaries defined by text and image checkers. By iteratively optimizing tokens near these boundaries, TCBS-Attack generates semantically coherent adversarial prompts capable of bypassing multiple defensive layers in T2I models. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art jailbreak attacks across various T2I models, including securely trained open-source models and commercial online services like DALL-E 3. TCBS-Attack achieves an ASR-4 of 45\% and an ASR-1 of 21\% on jailbreaking full-chain T2I models, significantly surpassing baseline methods.

Xiaobin Li, Kai Wu, Yujian Betterest Li et al.

Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It is crucial to ensure reliable and robust performance in various applications. Current optimizers often struggle with zero-shot optimization and require intricate hyperparameter tuning to adapt to new tasks. To address this, we propose a Pretrained Optimization Model (POM) that leverages knowledge gained from optimizing diverse tasks, offering efficient solutions to zero-shot optimization through direct application or fine-tuning with few-shot samples. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that POM outperforms state-of-the-art black-box optimization methods, especially for high-dimensional tasks. Fine-tuning POM with a small number of samples and budget yields significant performance improvements. Moreover, POM demonstrates robust generalization across diverse task distributions, dimensions, population sizes, and optimization horizons. For code implementation, see https://github.com/ninja-wm/POM/.

Jialin Wu, Jian Yang, Handing Wang et al.

Model merging combines expert models for multitask performance but faces challenges from parameter interference. This has sparked recent interest in controllable model merging, giving users the ability to explicitly balance performance trade-offs. Existing approaches employ a compile-then-query paradigm, performing a costly offline multi-objective optimization to enable fast, preference-aware model generation. This offline stage typically involves iterative search or dedicated training, with complexity that grows exponentially with the number of tasks. To overcome these limitations, we shift the perspective from parameter-space optimization to a direct correction of the model's final representation. Our approach models this correction as an optimal linear transformation, yielding a closed-form solution that replaces the entire offline optimization process with a single-step, architecture-agnostic computation. This solution directly incorporates user preferences, allowing a Pareto-optimal model to be generated on-the-fly with complexity that scales linearly with the number of tasks. Experimental results show our method generates a superior Pareto front with more precise preference alignment and drastically reduced computational cost.

Zhaoxin Wang, Handing Wang, Cong Tian et al.

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into less aligned modalities, such as vision. As MLLMs increasingly incorporate cross-modal consistency and alignment mechanisms, such explicit attacks become easier to detect and block. In this work, we propose a novel implicit jailbreak framework termed IJA that stealthily embeds malicious instructions into images via least significant bit steganography and couples them with seemingly benign, image-related textual prompts. To further enhance attack effectiveness across diverse MLLMs, we incorporate adversarial suffixes generated by a surrogate model and introduce a template optimization module that iteratively refines both the prompt and embedding based on model feedback. On commercial models like GPT-4o and Gemini-1.5 Pro, our method achieves attack success rates of over 90% using an average of only 3 queries.

Haoran Gu, Handing Wang, Yi Mei et al.

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context algorithm have shown strong performance and efficiency. However, inappropriate preference representations and training with imbalanced reward scores limit the performance of such algorithms. In this work, we introduce ParetoHqD that addresses the above issues by representing human preferences as preference directions in the objective space and regarding data near the Pareto front as ''high-quality'' data. For each preference, ParetoHqD follows a two-stage supervised fine-tuning process, where each stage uses an individual Pareto high-quality training set that best matches its preference direction. The experimental results have demonstrated the superiority of ParetoHqD over five baselines on two multiobjective alignment tasks.

Haoran Gu, Handing Wang, Yi Mei et al.

Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the models into generating harmful responses despite safety alignment. Recent studies have shown that current safety-aligned LLMs often undergo the shallow safety alignment, where the first few tokens largely determine whether the response will be harmful. Through comprehensive observations, we find that safety-aligned LLMs and various defense strategies generate highly similar initial tokens in their refusal responses, which we define as safety trigger tokens. Building on this insight, we propose \texttt{D-STT}, a simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens of the given safety-aligned LLM to trigger the model's learned safety patterns. In this process, the safety trigger is constrained to a single token, which effectively preserves model usability by introducing minimum intervention in the decoding process. Extensive experiments across diverse jailbreak attacks and benign prompts demonstrate that \ours significantly reduces output harmfulness while preserving model usability and incurring negligible response time overhead, outperforming ten baseline methods.