SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this work, we conduct the first comprehensive study evaluating the vulnerability of fine-tuned LLMs to membership inference attacks (MIAs). Our empirical analysis demonstrates that MIAs exploit the loss reduction during fine-tuning, making them highly effective in revealing membership information. These findings motivate the development of our defense. We propose SOFT (\textbf{S}elective data \textbf{O}bfuscation in LLM \textbf{F}ine-\textbf{T}uning), a novel defense technique that mitigates privacy leakage by leveraging influential data selection with an adjustable parameter to balance utility preservation and privacy protection. Our extensive experiments span six diverse domains and multiple LLM architectures and scales. Results show that SOFT effectively reduces privacy risks while maintaining competitive model performance, offering a practical and scalable solution to safeguard sensitive information in fine-tuned LLMs.

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the overall efficiency and accuracy of content review. However, existing resources for harmful content detection are predominantly focused on English, with Chinese datasets remaining scarce and often limited in scope. We present a comprehensive, professionally annotated benchmark for Chinese content harm detection, which covers six representative categories and is constructed entirely from real-world data. Our annotation process further yields a knowledge rule base that provides explicit expert knowledge to assist LLMs in Chinese harmful content detection. In addition, we propose a knowledge-augmented baseline that integrates both human-annotated knowledge rules and implicit knowledge from large language models, enabling smaller models to achieve performance comparable to state-of-the-art LLMs. Code and data are available at https://github.com/zjunlp/ChineseHarm-bench.

CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling

Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of sending these model updates may leak client's private data information. Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client's gradient vectors. Recently, researchers have proposed advanced gradient inversion techniques that existing defenses struggle to handle effectively. In this work, we present a novel defense tailored for large neural network models. Our defense capitalizes on the high dimensionality of the model parameters to perturb gradients within a subspace orthogonal to the original gradient. By leveraging cold posteriors over orthogonal subspaces, our defense implements a refined gradient update mechanism. This enables the selection of an optimal gradient that not only safeguards against gradient inversion attacks but also maintains model utility. We conduct comprehensive experiments across three different datasets and evaluate our defense against various state-of-the-art attacks and defenses. Code is available at https://censor-gradient.github.io.

DIGIMON: Diagnosis and Mitigation of Sampling Skew for Reinforcement Learning based Meta-Planner in Robot Navigation

Robot navigation is increasingly crucial across applications like delivery services and warehouse management. The integration of Reinforcement Learning (RL) with classical planning has given rise to meta-planners that combine the adaptability of RL with the explainable decision-making of classical planners. However, the exploration capabilities of RL-based meta-planners during training are often constrained by the capabilities of the underlying classical planners. This constraint can result in limited exploration, thereby leading to sampling skew issues. To address these issues, our paper introduces a novel framework, DIGIMON, which begins with behavior-guided diagnosis for exploration bottlenecks within the meta-planner and follows up with a mitigation strategy that conducts up-sampling from diagnosed bottleneck data. Our evaluation shows 13.5%+ improvement in navigation performance, greater robustness in out-of-distribution environments, and a 4x boost in training efficiency. DIGIMON is designed as a versatile, plug-and-play solution, allowing seamless integration into various RL-based meta-planners.

ROCAS: Root Cause Analysis of Autonomous Driving Accidents via Cyber-Physical Co-mutation

As Autonomous driving systems (ADS) have transformed our daily life, safety of ADS is of growing significance. While various testing approaches have emerged to enhance the ADS reliability, a crucial gap remains in understanding the accidents causes. Such post-accident analysis is paramount and beneficial for enhancing ADS safety and reliability. Existing cyber-physical system (CPS) root cause analysis techniques are mainly designed for drones and cannot handle the unique challenges introduced by more complex physical environments and deep learning models deployed in ADS. In this paper, we address the gap by offering a formal definition of ADS root cause analysis problem and introducing ROCAS, a novel ADS root cause analysis framework featuring cyber-physical co-mutation. Our technique uniquely leverages both physical and cyber mutation that can precisely identify the accident-trigger entity and pinpoint the misconfiguration of the target ADS responsible for an accident. We further design a differential analysis to identify the responsible module to reduce search space for the misconfiguration. We study 12 categories of ADS accidents and demonstrate the effectiveness and efficiency of ROCAS in narrowing down search space and pinpointing the misconfiguration. We also show detailed case studies on how the identified misconfiguration helps understand rationale behind accidents.

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen target label. While existing works have proposed various methods to mitigate backdoor effects in poisoned models, they tend to be less effective against recent advanced attacks. In this paper, we introduce a novel post-training defense technique UNIT that can effectively eliminate backdoor effects for a variety of attacks. In specific, UNIT approximates a unique and tight activation distribution for each neuron in the model. It then proactively dispels substantially large activation values that exceed the approximated boundaries. Our experimental results demonstrate that UNIT outperforms 7 popular defense methods against 14 existing backdoor attacks, including 2 advanced attacks, using only 5\% of clean training data. UNIT is also cost efficient. The code is accessible at https://github.com/Megum1/UNIT.

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. However, current unlearning paradigms are mired in vague forgetting boundaries, often erasing knowledge indiscriminately. In this work, we introduce KnowUnDo, a benchmark containing copyrighted content and user privacy domains to evaluate if the unlearning process inadvertently erases essential knowledge. Our findings indicate that existing unlearning methods often suffer from excessive unlearning. To address this, we propose a simple yet effective method, MemFlex, which utilizes gradient information to precisely target and unlearn sensitive parameters. Experimental results show that MemFlex is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs. Code and dataset will be released at https://github.com/zjunlp/KnowUnDo.

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks typically leverage a universal trigger pattern or transformation function, such that the trigger can cause misclassification for any input. In response to this, recent papers have introduced attacks using sample-specific invisible triggers crafted through special transformation functions. While these approaches manage to evade detection to some extent, they reveal vulnerability to existing backdoor mitigation techniques. To address and enhance both evasiveness and resilience, we introduce a novel backdoor attack LOTUS. Specifically, it leverages a secret function to separate samples in the victim class into a set of partitions and applies unique triggers to different partitions. Furthermore, LOTUS incorporates an effective trigger focusing mechanism, ensuring only the trigger corresponding to the partition can induce the backdoor behavior. Extensive experimental results show that LOTUS can achieve high attack success rate across 4 datasets and 7 model structures, and effectively evading 13 backdoor detection and mitigation techniques. The code is available at https://github.com/Megum1/LOTUS.

InstructEdit: Instruction-based Knowledge Editing for Large Language Models

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approach encounters issues with limited generalizability across tasks, necessitating one distinct editor for each task, which significantly hinders the broader applications. To address this, we take the first step to analyze the multi-task generalization issue in knowledge editing. Specifically, we develop an instruction-based editing technique, termed InstructEdit, which facilitates the editor's adaptation to various task performances simultaneously using simple instructions. With only one unified editor for each LLM, we empirically demonstrate that InstructEdit can improve the editor's control, leading to an average 14.86% increase in Reliability in multi-task editing setting. Furthermore, experiments involving holdout unseen task illustrate that InstructEdit consistently surpass previous strong baselines. To further investigate the underlying mechanisms of instruction-based knowledge editing, we analyze the principal components of the editing gradient directions, which unveils that instructions can help control optimization direction with stronger OOD generalization. Code and datasets will be available in https://github.com/zjunlp/EasyEdit.

MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing

Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving the intricacies of fine-grained (FG) multimodal entity knowledge largely unexplored. This gap presents a notable challenge, as FG entity recognition is pivotal for the practical deployment and effectiveness of MLLMs in diverse real-world scenarios. To bridge this gap, we introduce MIKE, a comprehensive benchmark and dataset specifically designed for the FG multimodal entity knowledge editing. MIKE encompasses a suite of tasks tailored to assess different perspectives, including Vanilla Name Answering, Entity-Level Caption, and Complex-Scenario Recognition. In addition, a new form of knowledge editing, Multi-step Editing, is introduced to evaluate the editing efficiency. Through our extensive evaluations, we demonstrate that the current state-of-the-art methods face significant challenges in tackling our proposed benchmark, underscoring the complexity of FG knowledge editing in MLLMs. Our findings spotlight the urgent need for novel approaches in this domain, setting a clear agenda for future research and development efforts within the community.