arXiv subjects

Yi Zeng

Publications and source records attributed to Yi Zeng.

At least 127 records · Page 7Linked to original sources

arXiv2024

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse range of malicious behaviors make this a critical challenge. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations. Experiments show BEEAR reduces the success rate of RLHF time backdoor attacks from >95% to <1% and from 47% to 0% for instruction-tuning time backdoors targeting malicious code generation, without compromising model utility. Requiring only defender-defined safe and unwanted behaviors, BEEAR represents a step towards practical defenses against safety backdoors in LLMs, providing a foundation for further advancements in AI safety and security.

cs.CR↗

arXiv2024

Fairness-Aware Meta-Learning via Nash Bargaining

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set. Such an adjustment procedure can be cast within a meta-learning framework. However, naive integration of fairness goals via meta-learning can cause hypergradient conflicts for subgroups, resulting in unstable convergence and compromising model performance and fairness. To navigate this issue, we frame the resolution of hypergradient conflicts as a multi-player cooperative bargaining game. We introduce a two-stage meta-learning framework in which the first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model toward the Pareto front, and the second stage optimizes with respect to specific fairness goals. Our method is supported by theoretical results, notably a proof of the NBS for gradient aggregation free from linear independence assumptions, a proof of Pareto improvement, and a proof of monotonic improvement in validation loss. We also show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.

cs.LG↗

arXiv2024

Parallel Spiking Unit for Efficient Training of Spiking Neural Networks

Efficient parallel computing has become a pivotal element in advancing artificial intelligence. Yet, the deployment of Spiking Neural Networks (SNNs) in this domain is hampered by their inherent sequential computational dependency. This constraint arises from the need for each time step's processing to rely on the preceding step's outcomes, significantly impeding the adaptability of SNN models to massively parallel computing environments. Addressing this challenge, our paper introduces the innovative Parallel Spiking Unit (PSU) and its two derivatives, the Input-aware PSU (IPSU) and Reset-aware PSU (RPSU). These variants skillfully decouple the leaky integration and firing mechanisms in spiking neurons while probabilistically managing the reset process. By preserving the fundamental computational attributes of the spiking neuron model, our approach enables the concurrent computation of all membrane potential instances within the SNN, facilitating parallel spike output generation and substantially enhancing computational efficiency. Comprehensive testing across various datasets, including static and sequential images, Dynamic Vision Sensor (DVS) data, and speech datasets, demonstrates that the PSU and its variants not only significantly boost performance and simulation speed but also augment the energy efficiency of SNNs through enhanced sparsity in neural activity. These advancements underscore the potential of our method in revolutionizing SNN deployment for high-performance parallel computing applications.

cs.NE↗

arXiv2024

Spiking Neural Networks with Consistent Mapping Relations Allow High-Accuracy Inference

Spike-based neuromorphic hardware has demonstrated substantial potential in low energy consumption and efficient inference. However, the direct training of deep spiking neural networks is challenging, and conversion-based methods still require substantial time delay owing to unresolved conversion errors. We determine that the primary source of the conversion errors stems from the inconsistency between the mapping relationship of traditional activation functions and the input-output dynamics of spike neurons. To counter this, we introduce the Consistent ANN-SNN Conversion (CASC) framework. It includes the Consistent IF (CIF) neuron model, specifically contrived to minimize the influence of the stable point's upper bound, and the wake-sleep conversion (WSC) method, synergistically ensuring the uniformity of neuron behavior. This method theoretically achieves a loss-free conversion, markedly diminishing time delays and improving inference performance in extensive classification and object detection tasks. Our approach offers a viable pathway toward more efficient and effective neuromorphic systems.

cs.NE↗

arXiv2024

BrainKnow -- Extracting, Linking, and Synthesizing Neuroscience Knowledge

The exponential growth of neuroscience literature presents a significant challenge for researchers seeking to efficiently access and utilize relevant information. To address this issue, we introduce the Brain Knowledge Engine (BrainKnow), an automated system designed to extract, link, and synthesize neuroscience knowledge from scientific publications. BrainKnow constructs a comprehensive knowledge graph encompassing 3,626,931 relationships across 37,011 neuroscience concepts, derived from 1,817,744 articles. This vast repository of knowledge is accessible through a user-friendly web interface, facilitating efficient navigation and data retrieval. BrainKnow employs advanced graph network algorithms, specifically Node2Vec, to enhance knowledge recommendation and visualization. This enables users to explore semantic relationships between concepts, predict potential new relationships, and gain a deeper understanding of the interconnectedness within neuroscience. Additionally, BrainKnow ensures real-time updates by synchronizing with PubMed, providing researchers with access to the most current information. BrainKnow serves as a valuable resource for neuroscience researchers, offering a powerful tool for exploring, synthesizing, and leveraging the vast and complex knowledge base of the field.

cs.DL↗

arXiv2024

JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits

In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient information and the closed-source nature of many diffusion models. To address this issue, we introduce JIGMARK. This first-of-its-kind watermarking technique enhances robustness through contrastive learning with pairs of images, processed and unprocessed by diffusion models, without needing a direct backpropagation of the diffusion process. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits, demonstrating a True Positive Rate more than triple that of leading baselines at a 1% False Positive Rate while preserving image quality. At the same time, it consistently improves the robustness against other conventional perturbations (like JPEG, blurring, etc.) and malicious watermark attacks over the state-of-the-art, often by a large margin. Furthermore, we propose the Human Aligned Variation (HAV) score, a new metric that surpasses traditional similarity measures in quantifying the number of image derivatives from image editing.

cs.CV↗

arXiv2024

AI Risk Management Should Incorporate Both Safety and Security

The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security. Although the two disciplines now come together under the overarching goal of AI risk management, they have historically evolved separately, giving rise to differing perspectives. Therefore, in this paper, we advocate that stakeholders in AI risk management should be aware of the nuances, synergies, and interplay between safety and security, and unambiguously take into account the perspectives of both disciplines in order to devise mostly effective and holistic risk mitigation approaches. Unfortunately, this vision is often obfuscated, as the definitions of the basic concepts of "safety" and "security" themselves are often inconsistent and lack consensus across communities. With AI risk management being increasingly cross-disciplinary, this issue is particularly salient. In light of this conceptual challenge, we introduce a unified reference framework to clarify the differences and interplay between AI safety and AI security, aiming to facilitate a shared understanding and effective collaboration across communities.

cs.CR↗

arXiv2024

Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation

This paper presents a novel approach leveraging Spiking Neural Networks (SNNs) to construct a Variational Quantized Autoencoder (VQ-VAE) with a temporal codebook inspired by hippocampal time cells. This design captures and utilizes temporal dependencies, significantly enhancing the generative capabilities of SNNs. Neuroscientific research has identified hippocampal "time cells" that fire sequentially during temporally structured experiences. Our temporal codebook emulates this behavior by triggering the activation of time cell populations based on similarity measures as input stimuli pass through it. We conducted extensive experiments on standard benchmark datasets, including MNIST, FashionMNIST, CIFAR10, CelebA, and downsampled LSUN Bedroom, to validate our model's performance. Furthermore, we evaluated the effectiveness of the temporal codebook on neuromorphic datasets NMNIST and DVS-CIFAR10, and demonstrated the model's capability with high-resolution datasets such as CelebA-HQ, LSUN Bedroom, and LSUN Church. The experimental results indicate that our method consistently outperforms existing SNN-based generative models across multiple datasets, achieving state-of-the-art performance. Notably, our approach excels in generating high-resolution and temporally consistent data, underscoring the crucial role of temporal information in SNN-based generative modeling.

cs.NE↗

arXiv2024

Introducing v0.5 of the AI Safety Benchmark from MLCommons

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.

cs.CL↗

arXiv2024

TIM: An Efficient Temporal Interaction Module for Spiking Transformer

Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets. The integration of attention mechanisms, inspired by advancements in neural network architectures, has led to the development of Spiking Transformers. These have shown promise in enhancing SNNs' capabilities, particularly in the realms of both static and neuromorphic datasets. Despite their progress, a discernible gap exists in these systems, specifically in the Spiking Self Attention (SSA) mechanism's effectiveness in leveraging the temporal processing potential of SNNs. To address this, we introduce the Temporal Interaction Module (TIM), a novel, convolution-based enhancement designed to augment the temporal data processing abilities within SNN architectures. TIM's integration into existing SNN frameworks is seamless and efficient, requiring minimal additional parameters while significantly boosting their temporal information handling capabilities. Through rigorous experimentation, TIM has demonstrated its effectiveness in exploiting temporal information, leading to state-of-the-art performance across various neuromorphic datasets. The code is available at https://github.com/BrainCog-X/Brain-Cog/tree/main/examples/TIM.

cs.NE↗

arXiv2024

Towards a Novel Perspective on Adversarial Examples Driven by Frequency

Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adversarial examples is through a frequency-based approach. However, existing research indicates that attacks designed to exploit low-frequency or high-frequency information can enhance attack performance, leading to an unclear relationship between adversarial perturbations and different frequency components. In this paper, we seek to demystify this relationship by exploring the characteristics of adversarial perturbations within the frequency domain. We employ wavelet packet decomposition for detailed frequency analysis of adversarial examples and conduct statistical examinations across various frequency bands. Intriguingly, our findings indicate that significant adversarial perturbations are present within the high-frequency components of low-frequency bands. Drawing on this insight, we propose a black-box adversarial attack algorithm based on combining different frequency bands. Experiments conducted on multiple datasets and models demonstrate that combining low-frequency bands and high-frequency components of low-frequency bands can significantly enhance attack efficiency. The average attack success rate reaches 99\%, surpassing attacks that utilize a single frequency segment. Additionally, we introduce the normalized disturbance visibility index as a solution to the limitations of $L_2$ norm in assessing continuous and discrete perturbations.

cs.LG↗

arXiv2024

Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning

Fine-tuning techniques based on Large Pretrained Language Models (LPLMs) have been proven to significantly enhance model performance on a variety of downstream tasks and effectively control the output behaviors of LPLMs. Recent studies have proposed numerous methods for fine-tuning a small number of parameters based on open-source LPLMs, reducing the demand for computational and storage resources. Among these, reparameterization fine-tuning methods represented by LoRA (Low-Rank Adaptation) have gained popularity. We find that although these methods perform well in many aspects, there is still considerable room for improvement in terms of complex task adaptability, performance, stability, and algorithm complexity. In response to this, inspired by the idea that the functions of the brain are shaped by its geometric structure, this paper integrates this idea into LoRA technology and proposes a new matrix transformation-based reparameterization method for efficient fine-tuning, named Matrix-Transformation based Low-Rank Adaptation (MTLoRA). MTLoRA aims to dynamically alter its spatial geometric structure by applying a transformation-matrix T to perform linear transformations, such as rotation, scaling, and translation, on the task-specific parameter matrix, generating new matrix feature patterns (eigenvectors) to mimic the fundamental influence of complex geometric structure feature patterns in the brain on functions, thereby enhancing the model's performance in downstream tasks. In Natural Language Understanding (NLU) tasks, it is evaluated using the GLUE benchmark test, and the results reveal that MTLoRA achieves an overall performance increase of about 1.0% across eight tasks; in Natural Language Generation (NLG) tasks, MTLoRA improves performance by an average of 0.95% and 0.56% in the DART and WebNLG tasks, respectively.

cs.CL↗

arXiv2024

Multiple Latent Space Mapping for Compressed Dark Image Enhancement

Dark image enhancement aims at converting dark images to normal-light images. Existing dark image enhancement methods take uncompressed dark images as inputs and achieve great performance. However, in practice, dark images are often compressed before storage or transmission over the Internet. Current methods get poor performance when processing compressed dark images. Artifacts hidden in the dark regions are amplified by current methods, which results in uncomfortable visual effects for observers. Based on this observation, this study aims at enhancing compressed dark images while avoiding compression artifacts amplification. Since texture details intertwine with compression artifacts in compressed dark images, detail enhancement and blocking artifacts suppression contradict each other in image space. Therefore, we handle the task in latent space. To this end, we propose a novel latent mapping network based on variational auto-encoder (VAE). Firstly, different from previous VAE-based methods with single-resolution features only, we exploit multiple latent spaces with multi-resolution features, to reduce the detail blur and improve image fidelity. Specifically, we train two multi-level VAEs to project compressed dark images and normal-light images into their latent spaces respectively. Secondly, we leverage a latent mapping network to transform features from compressed dark space to normal-light space. Specifically, since the degradation models of darkness and compression are different from each other, the latent mapping process is divided mapping into enlightening branch and deblocking branch. Comprehensive experiments demonstrate that the proposed method achieves state-of-the-art performance in compressed dark image enhancement.

cs.CV↗

arXiv2024

A Safe Harbor for AI Evaluation and Red Teaming

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives on good faith safety evaluations. This causes some researchers to fear that conducting such research or releasing their findings will result in account suspensions or legal reprisal. Although some companies offer researcher access programs, they are an inadequate substitute for independent research access, as they have limited community representation, receive inadequate funding, and lack independence from corporate incentives. We propose that major AI developers commit to providing a legal and technical safe harbor, indemnifying public interest safety research and protecting it from the threat of account suspensions or legal reprisal. These proposals emerged from our collective experience conducting safety, privacy, and trustworthiness research on generative AI systems, where norms and incentives could be better aligned with public interests, without exacerbating model misuse. We believe these commitments are a necessary step towards more inclusive and unimpeded community efforts to tackle the risks of generative AI.

cs.AI↗

arXiv2024

An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes SNNs prone to overfitting and limits their performance. In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data. In this paper, we first discuss the domain mismatch problem encountered when directly transferring networks trained on static datasets to event data. We argue that the inconsistency of feature distributions becomes a major factor hindering the effective transfer of knowledge from static images to event data. To address this problem, we propose solutions in terms of two aspects: feature distribution and training strategy. Firstly, we propose a knowledge transfer loss, which consists of domain alignment loss and spatio-temporal regularization. The domain alignment loss learns domain-invariant spatial features by reducing the marginal distribution distance between the static image and the event data. Spatio-temporal regularization provides dynamically learnable coefficients for domain alignment loss by using the output features of the event data at each time step as a regularization term. In addition, we propose a sliding training strategy, which gradually replaces static image inputs probabilistically with event data, resulting in a smoother and more stable training for the network. We validate our method on neuromorphic datasets, including N-Caltech101, CEP-DVS, and N-Omniglot. The experimental results show that our proposed method achieves better performance on all datasets compared to the current state-of-the-art methods. Code is available at https://github.com/Brain-Cog-Lab/Transfer-for-DVS.

cs.CV↗

arXiv2024

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

The evolution of the human brain has led to the development of complex synaptic plasticity, enabling dynamic adaptation to a constantly evolving world. This progress inspires our exploration into a new paradigm for Spiking Neural Networks (SNNs): a Plasticity-Driven Learning Framework (PDLF). This paradigm diverges from traditional neural network models that primarily focus on direct training of synaptic weights, leading to static connections that limit adaptability in dynamic environments. Instead, our approach delves into the heart of synaptic behavior, prioritizing the learning of plasticity rules themselves. This shift in focus from weight adjustment to mastering the intricacies of synaptic change offers a more flexible and dynamic pathway for neural networks to evolve and adapt. Our PDLF does not merely adapt existing concepts of functional and Presynaptic-Dependent Plasticity but redefines them, aligning closely with the dynamic and adaptive nature of biological learning. This reorientation enhances key cognitive abilities in artificial intelligence systems, such as working memory and multitasking capabilities, and demonstrates superior adaptability in complex, real-world scenarios. Moreover, our framework sheds light on the intricate relationships between various forms of plasticity and cognitive functions, thereby contributing to a deeper understanding of the brain's learning mechanisms. Integrating this groundbreaking plasticity-centric approach in SNNs marks a significant advancement in the fusion of neuroscience and artificial intelligence. It paves the way for developing AI systems that not only learn but also adapt in an ever-changing world, much like the human brain.

cs.NE↗

arXiv2024

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can also impose risks during daily interactions. This paper introduces a new perspective to jailbreak LLMs as human-like communicators, to explore this overlooked intersection between everyday language interaction and AI safety. Specifically, we study how to persuade LLMs to jailbreak them. First, we propose a persuasion taxonomy derived from decades of social science research. Then, we apply the taxonomy to automatically generate interpretable persuasive adversarial prompts (PAP) to jailbreak LLMs. Results show that persuasion significantly increases the jailbreak performance across all risk categories: PAP consistently achieves an attack success rate of over $92\%$ on Llama 2-7b Chat, GPT-3.5, and GPT-4 in $10$ trials, surpassing recent algorithm-focused attacks. On the defense side, we explore various mechanisms against PAP and, found a significant gap in existing defenses, and advocate for more fundamental mitigation for highly interactive LLMs

cs.CL↗

arXiv2024

A Brain-inspired Computational Model for Human-like Concept Learning

Concept learning is a fundamental aspect of human cognition and plays a critical role in mental processes such as categorization, reasoning, memory, and decision-making. Researchers across various disciplines have shown consistent interest in the process of concept acquisition in individuals. To elucidate the mechanisms involved in human concept learning, this study examines the findings from computational neuroscience and cognitive psychology. These findings indicate that the brain's representation of concepts relies on two essential components: multisensory representation and text-derived representation. These two types of representations are coordinated by a semantic control system, ultimately leading to the acquisition of concepts. Drawing inspiration from this mechanism, the study develops a human-like computational model for concept learning based on spiking neural networks. By effectively addressing the challenges posed by diverse sources and imbalanced dimensionality of the two forms of concept representations, the study successfully attains human-like concept representations. Tests involving similar concepts demonstrate that our model, which mimics the way humans learn concepts, yields representations that closely align with human cognition.

cs.AI↗