Search

Scientific discovery is a catalyst for human intellectual advances, driven by the cycle of hypothesis generation, experimental design, data evaluation, and iterative assumption refinement. This process, while crucial, is expensive and heavily dependent on the domain knowledge of scientists to generate hypotheses and navigate the scientific cycle. Central to this is causality, the ability to establish the relationship between the cause and the effect. Motivated by the scientific discovery process, in this work, we formulate a novel task where the input is a partial causal graph with missing variables, and the output is a hypothesis about the missing variables to complete the partial graph. We design a benchmark with varying difficulty levels and knowledge assumptions about the causal graph. With the growing interest in using Large Language Models (LLMs) to assist in scientific discovery, we benchmark open-source and closed models on our testbed. We show the strong ability of LLMs to hypothesize the mediation variables between a cause and its effect. In contrast, they underperform in hypothesizing the cause and effect variables themselves. We also observe surprising results where some of the open-source models outperform the closed GPT-4 model., Comment: Code - https://github.com/ivaxi0s/hypothesizing-causal-variable-llm

Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.

Large Language Models (LLMs) are routinely used in retrieval-augmented applications to orchestrate tasks and process inputs from users and other sources. These inputs, even in a single LLM interaction, can come from a variety of sources, of varying trustworthiness and provenance. This opens the door to prompt injection attacks, where the LLM receives and acts upon instructions from supposedly data-only sources, thus deviating from the user's original instructions. We define this as task drift, and we propose to catch it by scanning and analyzing the LLM's activations. We compare the LLM's activations before and after processing the external input in order to detect whether this input caused instruction drift. We develop two probing methods and find that simply using a linear classifier can detect drift with near perfect ROC AUC on an out-of-distribution test set. We show that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions, without being trained on any of these attacks. Our setup does not require any modification of the LLM (e.g., fine-tuning) or any text generation, thus maximizing deployability and cost efficiency and avoiding reliance on unreliable model output. To foster future research on activation-based task inspection, decoding, and interpretability, we will release our large-scale TaskTracker toolkit, comprising a dataset of over 500K instances, representations from 5 SoTA language models, and inspection tools.

Instruction-tuned Large Language Models (LLMs) show impressive results in numerous practical applications, but they lack essential safety features that are common in other areas of computer science, particularly an explicit separation of instructions and data. This makes them vulnerable to manipulations such as indirect prompt injections and generally unsuitable for safety-critical tasks. Surprisingly, there is currently no established definition or benchmark to quantify this phenomenon. In this work, we close this gap by introducing a formal measure for instruction-data separation and an empirical variant that is calculable from a model's outputs. We also present a new dataset, SEP, that allows estimating the measure for real-world models. Our results on various LLMs show that the problem of instruction-data separation is real: all models fail to achieve high separation, and canonical mitigation techniques, such as prompt engineering and fine-tuning, either fail to substantially improve separation or reduce model utility. The source code and SEP dataset are openly accessible at https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed., Comment: GitHub: https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed. 10 pages main text, 30 pages in total

Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact. Understanding the non-deliberate(ive) mechanism of LLMs in giving responses is essential in explaining their performance and discerning their biases in real-world applications. This is analogous to human studies, where such inadvertent responses are referred to as sampling. We study this sampling of LLMs in light of value bias and show that the sampling of LLMs tends to favour high-value options. Value bias corresponds to this shift of response from the most likely towards an ideal value represented in the LLM. In fact, this effect can be reproduced even with new entities learnt via in-context prompting. We show that this bias manifests in unexpected places and has implications on relevant application scenarios, like choosing exemplars. The results show that value bias is strong in LLMs across different categories, similar to the results found in human studies.

There is an growing interest in using Large Language Models (LLMs) in multi-agent systems to tackle interactive real-world tasks that require effective collaboration and assessing complex situations. Yet, we still have a limited understanding of LLMs' communication and decision-making abilities in multi-agent setups. The fundamental task of negotiation spans many key features of communication, such as cooperation, competition, and manipulation potentials. Thus, we propose using scorable negotiation to evaluate LLMs. We create a testbed of complex multi-agent, multi-issue, and semantically rich negotiation games. To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities while integrating them in a dynamic and multi-turn setup. We propose multiple metrics to rigorously quantify agents' performance and alignment with the assigned role. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark. Importantly, we evaluate critical safety aspects such as the interaction dynamics between agents influenced by greedy and adversarial players. Our benchmark is highly challenging; GPT-3.5 and small models mostly fail, and GPT-4 and SoTA large models (e.g., Llama-3 70b) still underperform., Comment: Updated version with major additions (new experiments, evaluation, and attacks)

Clickbait PDFs are PDF documents that do not embed malware but trick victims into visiting malicious web pages leading to attacks like password theft or drive-by download. While recent reports indicate a surge of clickbait PDFs, prior works have largely neglected this new threat, considering PDFs only as accessories of email phishing campaigns. This paper investigates the landscape of clickbait PDFs and presents the first systematic and comprehensive study of this phenomenon. Starting from a real-world dataset, we identify 44 clickbait PDF clusters via clustering and characterize them by looking at their volumetric, temporal, and visual features. Among these, we identify three large clusters covering 89% of the dataset, exhibiting significantly different volumetric and temporal properties compared to classical email phishing, and relying on web UI elements as visual baits. Finally, we look at the distribution vectors and show that clickbait PDFs are not only distributed via attachments but also via Search Engine Optimization attacks, placing clickbait PDFs outside the email distribution ecosystem. Clickbait PDFs seem to be a lurking threat, not subjected to any form of content-based filtering or detection: AV scoring systems, like VirusTotal, rank them considerably low, creating a blind spot for organizations. While URL blocklists can help to prevent victims from visiting the attack web pages, we observe that they have a limited coverage., Comment: Corrected symbols in Table 1

We outline a planned experiment to investigate if personal data (e.g., demographics and behavioral patterns) can be used to selectively expose individuals to disinformation such that an adversary can spread disinformation more efficiently compared to broadcasting the same information to everyone. This mechanism, if effective, will have devastating consequences as modern technologies collect and infer a plethora of private data that can be abused to target with disinformation. We believe this research will inform designing policies and regulations for online platforms.

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial prompting, e.g., Prompt Injection (PI) attacks enable attackers to override original instructions and employed controls. So far, it was assumed that the user is directly prompting the LLM. But, what if it is not the user prompting? We argue that LLM-Integrated Applications blur the line between data and instructions. We reveal new attack vectors, using Indirect Prompt Injection, that enable adversaries to remotely (without a direct interface) exploit LLM-integrated applications by strategically injecting prompts into data likely to be retrieved. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities, including data theft, worming, information ecosystem contamination, and other novel security risks. We demonstrate our attacks' practical viability against both real-world systems, such as Bing's GPT-4 powered Chat and code-completion engines, and synthetic applications built on GPT-4. We show how processing retrieved prompts can act as arbitrary code execution, manipulate the application's functionality, and control how and if other APIs are called. Despite the increasing integration and reliance on LLMs, effective mitigations of these emerging threats are currently lacking. By raising awareness of these vulnerabilities and providing key insights into their implications, we aim to promote the safe and responsible deployment of these powerful models and the development of robust defenses that protect users and systems from potential attacks.

Mis- and disinformation are a substantial global threat to our security and safety. To cope with the scale of online misinformation, researchers have been working on automating fact-checking by retrieving and verifying against relevant evidence. However, despite many advances, a comprehensive evaluation of the possible attack vectors against such systems is still lacking. Particularly, the automated fact-verification process might be vulnerable to the exact disinformation campaigns it is trying to combat. In this work, we assume an adversary that automatically tampers with the online evidence in order to disrupt the fact-checking model via camouflaging the relevant evidence or planting a misleading one. We first propose an exploratory taxonomy that spans these two targets and the different threat model dimensions. Guided by this, we design and propose several potential attack methods. We show that it is possible to subtly modify claim-salient snippets in the evidence and generate diverse and claim-aligned evidence. Thus, we highly degrade the fact-checking performance under many different permutations of the taxonomy's dimensions. The attacks are also robust against post-hoc modifications of the claim. Our analysis further hints at potential limitations in models' inference when faced with contradicting evidence. We emphasize that these attacks can have harmful implications on the inspectable and human-in-the-loop usage scenarios of such models, and we conclude by discussing challenges and directions for future defenses.

Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and effective ways used by adversaries to spread viral false stories. In this threat, a real image is re-purposed to support other narratives by misrepresenting its context and/or elements. The internet is being used as the go-to way to verify information using different sources and modalities. Our goal is an inspectable method that automates this time-consuming and reasoning-intensive process by fact-checking the image-caption pairing using Web evidence. To integrate evidence and cues from both modalities, we introduce the concept of 'multi-modal cycle-consistency check'; starting from the image/caption, we gather textual/visual evidence, which will be compared against the other paired caption/image, respectively. Moreover, we propose a novel architecture, Consistency-Checking Network (CCN), that mimics the layered human reasoning across the same and different modalities: the caption vs. textual evidence, the image vs. visual evidence, and the image vs. caption. Our work offers the first step and benchmark for open-domain, content-based, multi-modal fact-checking, and significantly outperforms previous baselines that did not leverage external evidence., Comment: CVPR'22

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have been proposed, many have been shown ineffective. As these vulnerabilities are still nowhere near being eliminated, we propose an alternative deployment-based defense paradigm that goes beyond the traditional white-box and black-box threat models. Instead of training a single partially-robust model, one could train a set of same-functionality, yet, adversarially-disjoint models with minimal in-between attack transferability. These models could then be randomly and individually deployed, such that accessing one of them minimally affects the others. Our experiments on CIFAR-10 and a wide range of attacks show that we achieve a significantly lower attack transferability across our disjoint models compared to a baseline of ensemble diversity. In addition, compared to an adversarially trained set, we achieve a higher average robust accuracy while maintaining the accuracy of clean examples.

Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of such models for malicious purposes. In this paper, we study natural language watermarking as a defense to help better mark and trace the provenance of text. We introduce the Adversarial Watermarking Transformer (AWT) with a jointly trained encoder-decoder and adversarial training that, given an input text and a binary message, generates an output text that is unobtrusively encoded with the given message. We further study different training and inference strategies to achieve minimal changes to the semantics and correctness of the input text. AWT is the first end-to-end model to hide data in text by automatically learning -- without ground truth -- word substitutions along with their locations in order to encode the message. We empirically show that our model is effective in largely preserving text utility and decoding the watermark while hiding its presence against adversaries. Additionally, we demonstrate that our method is robust against a range of attacks.

Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. While existing research work on deepfake detection demonstrates high accuracy, it is subject to advances in generation techniques and adversarial iterations on detection countermeasure techniques. Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models. Our approach is simple and effective. We first embed artificial fingerprints into training data, then validate a surprising discovery on the transferability of such fingerprints from training data to generative models, which in turn appears in the generated deepfakes. Experiments show that our fingerprinting solution (1) holds for a variety of cutting-edge generative models, (2) leads to a negligible side effect on generation quality, (3) stays robust against image-level and model-level perturbations, (4) stays hard to be detected by adversaries, and (5) converts deepfake detection and attribution into trivial tasks and outperforms the recent state-of-the-art baselines. Our solution closes the responsibility loop between publishing pre-trained generative model inventions and their possible misuses, which makes it independent of the current arms race. Code and models are available at https://github.com/ningyu1991/ArtificialGANFingerprints ., Comment: Accepted to ICCV'21 as Oral

Phishing websites are still a major threat in today's Internet ecosystem. Despite numerous previous efforts, similarity-based detection methods do not offer sufficient protection for the trusted websites - in particular against unseen phishing pages. This paper contributes VisualPhishNet, a new similarity-based phishing detection framework, based on a triplet Convolutional Neural Network (CNN). VisualPhishNet learns profiles for websites in order to detect phishing websites by a similarity metric that can generalize to pages with new visual appearances. We furthermore present VisualPhish, the largest dataset to date that facilitates visual phishing detection in an ecologically valid manner. We show that our method outperforms previous visual similarity phishing detection approaches by a large margin while being robust against a range of evasion attacks.