Backdoor-Attack-Defense-LLMs

Interpretability-of-LLMs IBSD 是已发表论文"IBSD：针对后门攻击的可迭代黑盒自防御"（发表于 IEEE Signal Processing Letters，2025.10）的代码论文链接 SLIP 是已发表论文"SLIP：软标签机制与密钥提取引导的基于 CoT 的 API 指令后门防御"（发表于 2026-ACL-findings）的代码论文链接。 BeDKD 是已录用论文"BeDKD：基于方向映射模块与对抗知识蒸馏的后门防御"（发表于 2026-AAAI）的代码论文链接。 BadApex...

AKRASIA: Stealthy Backdoor Attack on Reasoning-Based Code LLMs

We present AKRASIA, a stealthy, inference-time backdoor attack against reasoning-based Code LLMs. AKRASIA aims to achieve a backdoor target e.g., malicious code execution in reasoning LLMs while evading automated defenses and human inspection. To achieve this, AKRASIA probes the victim LLM to...

Model Poisoning against Federated Model Adaptation with Chain of Bit-Flips

Federated Learning FL allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized actors may lead to poisoning attacks: clients controlled by malicious third party potentially poison the training...

BadBone: Backdoor Attacks against Backbone Models in Visual Prompt Learning

Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored. In this work, we take the first step to propose BadBone, ...

Backdooring Masked Diffusion Language Models

Masked diffusion language models MDLMs are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs...

MetaBackdoor: Exploiting Positional Encoding As a Backdoor Attack Surface in LLMs

Backdoor attacks pose a serious security threat to large language models LLMs, which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on content-based triggers, requiring explicit modification of the input...

DETOUR: A Practical Backdoor Attack against Object Detection

Object detection OD is critical to real-world vision systems, yet existing backdoor attacks on detection transformers DETRs for OD tasks rely on patch-wise triggers optimized at fixed locations with minimal perturbations. Such attacks overlook that backdoor triggers in the real world may appear a...

SlowBA: An Efficiency Backdoor Attack Towards VLM-Based GUI Agents

Modern vision-language-model VLM based graphical user interface GUI agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security...

Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning

Federated learning FL enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy concerns inherent in...

Backdoor Attacks on Contrastive Continual Learning for IoT Systems

The Internet of Things IoT systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial dynamics. Contrastive continual learning CCL combines contrastiv...

DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers

The widespread adoption of Vision Transformers ViTs elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Existing ViT backdoor attacks largely rely on poisoned-data training, while prior data-free attempts typically require...

Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models

Low-Rank Adaptation LoRA has emerged as an efficient method for fine-tuning large language models LLMs and is widely adopted within the open-source community. However, the decentralized dissemination of LoRA adapters through platforms such as Hugging Face introduces novel security vulnerabilities...

6DAttack: Backdoor Attacks in the 6DoF Pose Estimation

Deep learning advances have enabled accurate six-degree-of-freedom 6DoF object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks pose significant security risks. While most research focuses on 2D vision, 6DoF pose estimation remains largely...

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability and robustness due to their dependence on single-trigger-single-objec...

Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning

Reinforcement learning RL has achieved remarkable success across diverse domains, enabling autonomous systems to learn and adapt to dynamic environments by optimizing a reward function. However, this reliance on reward signals creates a significant security vulnerability. In this paper, we study ...

BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-Tuning

Knowledge Distillation KD is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks -- most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally...

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-To-End Autonomous Driving

Assessing the safety of autonomous driving AD systems against security threats, particularly backdoor attacks, is a stepping stone for real-world deployment. However, existing works mainly focus on pixel-level triggers that are impractical to deploy in the real world. We address this gap by...

Your Compiler Is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers

Deep learning DL compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified compiler alter a model's semantics during compilation and...

IAG: Input-Aware Backdoor Attack on VLMs for Visual Grounding

Vision-language models VLMs have shown significant advancements in tasks such as visual grounding, where they localize specific objects in images based on natural language queries and images. However, security issues in visual grounding tasks for VLMs remain underexplored, especially in the conte...

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning

Active learningAL, which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for identifying the most important data to label. Despite this...