Large language models (LLMs) have transformed the field of natural language processing, but they remain susceptible to jailbreaking attacks that exploit their capabilities to generate unintended and potentially harmful content. Existing token-level jailbreaking techniques, while effective, face scalability and efficiency challenges, especially as models undergo frequent updates and incorporate advanced defensive measures. In this paper, we introduce JailMine, an innovative token-level manipulation approach that addresses these limitations effectively. JailMine employs an automated "mining" process to elicit malicious responses from LLMs by strategically selecting affirmative outputs and iteratively reducing the likelihood of rejection. Through rigorous testing across multiple well-known LLMs and datasets, we demonstrate JailMine's effectiveness and efficiency, achieving a significant average reduction of 86% in time consumed while maintaining high success rates averaging 95%, even in the face of evolving defensive strategies. Our work contributes to the ongoing effort to assess and mitigate the vulnerability of LLMs to jailbreaking attacks, underscoring the importance of continued vigilance and proactive measures to enhance the security and reliability of these powerful language models. 

pdf/lockpicking-llms-a-logit-based-jailbreak-using-token-level-2fg17rje3b.pdf

Lockpicking LLMs: A Logit-Based Jailbreak Using Token-level Manipulation

Large Language Models (LLMs) such as ChatGPT and its competitors have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. This survey provides a comprehensive overview of these emerging concerns, categorizing threats into several key areas: prompt injection and jailbreaking; adversarial attacks, including input perturbations and data poisoning; misuse by malicious actors to generate disinformation, phishing emails, and malware; and the worrisome risks inherent in autonomous LLM agents. Recently, a significant focus is increasingly being placed on the latter, exploring goal misalignment, emergent deception, self-preservation instincts, and the potential for LLMs to develop and pursue covert, misaligned objectives, a behavior known as scheming, which may even persist through safety training. We summarize recent academic and industrial studies from 2022 to 2025 that exemplify each threat, analyze proposed defenses and their limitations, and identify open challenges in securing LLM-based applications. We conclude by emphasizing the importance of advancing robust, multi-layered security strategies to ensure LLMs are safe and beneficial.

pdf/security-concerns-for-large-language-models-a-survey-8dpklfmzfby1.pdf

Security Concerns for Large Language Models: A Survey

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge from the user's intended goal, especially as external toolkits evolve. Traditional software testing assumes structured inputs and thus falls short in handling the ambiguity of natural language. We introduce TAI3, an API-centric stress testing framework that systematically uncovers intent integrity violations in LLM agents. Unlike prior work focused on fixed benchmarks or adversarial inputs, TAI3 generates realistic tasks based on toolkits'documentation and applies targeted mutations to expose subtle agent errors while preserving user intent. To guide testing, we propose semantic partitioning, which organizes natural language tasks into meaningful categories based on toolkit API parameters and their equivalence classes. Within each partition, seed tasks are mutated and ranked by a lightweight predictor that estimates the likelihood of triggering agent errors. To enhance efficiency, TAI3 maintains a datatype-aware strategy memory that retrieves and adapts effective mutation patterns from past cases. Experiments on 80 toolkit APIs demonstrate that TAI3 effectively uncovers intent integrity violations, significantly outperforming baselines in both error-exposing rate and query efficiency. Moreover, TAI3 generalizes well to stronger target models using smaller LLMs for test generation, and adapts to evolving APIs across domains.

pdf/intentest-stress-testing-for-intent-integrity-in-api-calling-b9cujxneqehl.pdf

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents

Artificial intelligence (AI) has seen significant progress in medical diagnostics, particularly in image and video analysis. This review focuses on the application of AI in analyzing in vivo confocal microscopy (IVCM) images for corneal diseases. The cornea, as an exposed and delicate part of the body, necessitates the precise diagnoses of various conditions. Convolutional neural networks (CNNs), a key component of deep learning, are a powerful tool for image data analysis. This review highlights AI applications in diagnosing keratitis, dry eye disease, and diabetic corneal neuropathy. It discusses the potential of AI in detecting infectious agents, analyzing corneal nerve morphology, and identifying the subtle changes in nerve fiber characteristics in diabetic corneal neuropathy. However, challenges still remain, including limited datasets, overfitting, low-quality images, and unrepresentative training datasets. This review explores augmentation techniques and the importance of feature engineering to address these challenges. Despite the progress made, challenges are still present, such as the “black-box” nature of AI models and the need for explainable AI (XAI). Expanding datasets, fostering collaborative efforts, and developing user-friendly AI tools are crucial for enhancing the acceptance and integration of AI into clinical practice.

Artificial-Intelligence-Enhanced Analysis of In Vivo Confocal Microscopy in Corneal Diseases: A Review

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs model security challenges. Although there is currently a large amount of research on prompt injection attacks, most of these black-box attacks use heuristic strategies. It is unclear how these heuristic strategies relate to the success rate of attacks and thus effectively improve model robustness. To solve this problem, we redefine the goal of the attack: to maximize the KL divergence between the conditional probabilities of the clean text and the adversarial text. Furthermore, we prove that maximizing the KL divergence is equivalent to maximizing the Mahalanobis distance between the embedded representation $x$ and $x'$ of the clean text and the adversarial text when the conditional probability is a Gaussian distribution and gives a quantitative relationship on $x$ and $x'$. Then we designed a simple and effective goal-guided generative prompt injection strategy (G2PIA) to find an injection text that satisfies specific constraints to achieve the optimal attack effect approximately. It is particularly noteworthy that our attack method is a query-free black-box attack method with low computational cost. Experimental results on seven LLM models and four datasets show the effectiveness of our attack method.

Goal-guided Generative Prompt Injection Attack on Large Language Models

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques have advanced from manual prompt engineering to automated methodologies. Recent advances have automated jailbreaking approaches that harness LLMs to generate jailbreak instructions and adversarial examples, delivering encouraging results. Nevertheless, these methods universally include an LLM generation phase, which, due to the complexities of deploying and reasoning with LLMs, impedes effective implementation and broader adoption. To mitigate this issue, we introduce \textbf{Adversarial Prompt Distillation}, an innovative framework that integrates masked language modeling, reinforcement learning, and dynamic temperature control to distill LLM jailbreaking prowess into smaller language models (SLMs). This methodology enables efficient, robust jailbreak attacks while maintaining high success rates and accommodating a broader range of application contexts. Empirical evaluations affirm the approach's superiority in attack efficacy, resource optimization, and cross-model versatility. Our research underscores the practicality of transferring jailbreak capabilities to SLMs, reveals inherent vulnerabilities in LLMs, and provides novel insights to advance LLM security investigations. Our code is available at: https://github.com/lxgem/Efficient_and_Stealthy_Jailbreak_Attacks_via_Adversarial_Prompt.

https://export.arxiv.org/pdf/2506.17231v2.pdf

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs

Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer unseen classes. However, we find that such existing models mostly produce imbalanced semantic predictions, i.e. these models could perform precisely for some semantics, but may not for others. To address the drawback, we aim to introduce an imbalanced learning framework into ZSL. However, we find that imbalanced ZSL has two unique challenges: (1) Its imbalanced predictions are highly correlated with the value of semantic labels rather than the number of samples as typically considered in the traditional imbalanced learning; (2) Different semantics follow quite different error distributions between classes. To mitigate these issues, we first formalize ZSL as an imbalanced regression problem which offers theoretical foundations to interpret how semantic labels lead to imbalanced semantic predictions. We then propose a re-weighted loss termed Re-balanced Mean-Squared Error (ReMSE), which tracks the mean and variance of error distributions, thus ensuring rebalanced learning across classes. As a major contribution, we conduct a series of analyses showing that ReMSE is theoretically well established. Extensive experiments demonstrate that the proposed method effectively alleviates the imbalance in semantic prediction and outperforms many state-of-the-art ZSL methods.

Rebalanced Zero-shot Learning

Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task. In recent years, AttnGAN based on the Attention mechanism to guide GAN training has been proposed, SD-GAN, which adopts a self-distillation technique to improve the performance of the generator and the quality of image generation, and Stack-GAN++, which gradually improves the details and quality of the image by stacking multiple generators and discriminators. However, this series of improvements to GAN all have redundancy to a certain extent, which affects the generation performance and complexity to a certain extent. We use the popular simple and effective idea (1) to remove redundancy structure and improve the backbone network of AttnGAN. (2) to integrate and reconstruct multiple losses of DAMSM. Our improvements have significantly improved the model size and training efficiency while ensuring that the model's performance is unchanged and finally proposed our SEAttnGAN. Code is avalilable at https://github.com/jmyissb/SEAttnGAN.

A Simple and Effective Baseline for Attentional Generative Adversarial Networks

The field of image blending has gained popularity in recent years for its ability to create visually stunning content. However, the current image blending algorithm has the following problems: 1) The manual creation of the image blending mask requires a lot of manpower and material resources; 2) The image blending algorithm cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method: it combines semantic object detection and segmentation with corresponding mask generation to automatically blend images, while a two-stage iterative algorithm based on our proposed new saturation loss and PAN algorithm to fix brightness distortion and low resolution issues. Results on publicly available datasets show that our method outperforms many classic image blending algorithms on various performance metrics such as PSNR and SSIM.

Automatic Image Blending Algorithm Based on SAM and DINO

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Xiaobo Jin

Author Tools

Chat about Author