搜索结果：Exploit

Security practitioners face growing challenges in exploit assessment, as public vulnerability repositories are increasingly populated with inconsistent and low-quality exploit artifacts. Existing scoring systems, such as CVSS and EPSS, offer limited support for this task. They either rely on theoretical metrics or produce opaque probability estimates without assessing whether usable exploit code exists. In practice, security teams often resort to manual triage of exploit repositories, which is time-consuming, error-prone, and difficult to scale. We present AEAS, an automated system designed to assess and prioritize actionable exploits through static analysis. AEAS analyzes both exploit code and associated documentation to extract a structured set of features reflecting exploit availability, functionality, and setup complexity. It then computes an actionability score for each exploit and produces ranked exploit recommendations. We evaluate AEAS on a dataset of over 5,000 vulnerabilities derived from 600+ real-world applications frequently encountered by red teams. Manual validation and expert review on representative subsets show that AEAS achieves a 100% top-3 success rate in recom

Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulnerability affected versions, they point out a key limitation that exploits are version-specific and cannot be directly applied across library versions. Despite being widely acknowledged, this limitation has not been systematically validated at scale, leaving the actual applicability of exploits across versions unexplored. To fill this gap, we conduct the first large-scale empirical study on exploit applicability across library versions. We construct a comprehensive dataset consisting of 259 exploits spanning 128 Java libraries and 28,150 historical versions, covering 61 CWEs that account for 76.33% of vulnerabilities in Maven. Leveraging this dataset, we execute each exploit against the library version history and compare the execution outcomes with our manually annotated ground-truth affected versions. We further investigate the root causes of inconsistencies between exploit execution and ground truth, and explore strategies for exploit migration. Our results (RQ1) show that, even without migration, explo

Poker is an imperfect information game that has served as a long-standing benchmark for decision-making under uncertainty. To maximize utility beyond the Nash equilibrium, an agent can deviate from Nash-equilibrium policies to exploit suboptimal play. We introduce AlphaExploitem, which extends the competitive RL poker agent AlphaHoldem by using a hierarchical transformer encoder that enables reasoning over previously played hands and modifying the training procedure with the inclusion of a diverse pool of exploitable opponents to facilitate learning to exploit. We train and evaluate AlphaExploitem on two standard benchmarks for imperfect-information games. Empirically, AlphaExploitem successfully exploits weak play by both in- and out-of-distribution opponents, without losing performance against NE opponents.

Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation. Existing automated exploit generation systems report binary pass/fail outcomes, discarding partial progress and producing no signal for the other two communities. This paper presents FORGE, a multi-agent system that bridges these three silos through graduated exploitation depth. Five specialized agents (Intel, Generator, Planner, Exploit, and Detector) execute in a fixed pipeline that (1) generates targeted vulnerable applications from CVE metadata, (2) conducts coached, multi-turn exploitation assessed by an LLM-primary oracle on a four-level taxonomy (L0: no evidence through L3: full compromise), and (3) produces Sigma and Snort detection rules grounded in OpenTelemetry exploitation traces. Graduated depth is the bridging mechanism: deeper exploitation yields richer behavioral traces for detection engineering, while depth data across scoring bands provides ground truth for prioritization validation. A tiered knowledge architecture accumul

Smart contract vulnerabilities in Decentralized Finance caused over billions of dollars losses every year, yet the security community faces a critical bottleneck: identifying a vulnerability is not the same as proving it is exploitable. Manual PoC construction is prohibitively labor-intensive, leaving most disclosed vulnerabilities unverified and protocols exposed long before mitigation is applied. In this paper, we propose \sys, a knowledge-driven agentic system for end-to-end contract vulnerability detection and exploit synthesis. Our core insight is that exploit synthesis is not a code generation task but a \emph{structured reasoning problem} that requires grounded knowledge of protocol semantics, failure root cause, and exploit primitives. \sys organizes this knowledge into a \emph{Hierarchical Knowledge Graph} (HKG) that serves as structured memory for LLM-guided multi-hop reasoning. To validate exploit feasibility beyond code synthesis, \sys employs a two-stage validation framework that checks exploit-path reachability via SMT solving and profit realizability via asset-level state simulation, ensuring generated PoCs satisfy both logical and economic viability constraints. Eva

Vulnerability exploits play a crucial role in assessing the downstream impact of Java library vulnerabilities. While some vulnerabilities are accompanied by disclosed exploit references, automatically reproducing such references into runnable exploits remains challenging because they are often incomplete, unstructured, or only describe partial reproduction steps. Recent code agents provide a promising way to automate this process, but our study shows that their generated exploits often appear successful without triggering the actual vulnerable logic, such as replacing vulnerable APIs with self-implemented functions. To address this, we propose Refploit, an LLM-based trajectory recovery framework for facilitating vulnerability reproduction from public exploit references. The key insight is that a failed agent trajectory is not entirely useless. It may have already completed some reproduction subtasks while also revealing misleading directions that should be avoided. Refploit first validates an agent-generated exploit through differential execution. When the exploit is ineffective, Refploit analyzes its reproduction progress, locates the trajectory segments associated with the reprod

We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach, constructing a high-quality dataset via multi-stage preprocessing and introducing a scalable evaluation framework with LLM-as-judge and fine-grained rubrics. Under this unified setup, we benchmark 17 large language models across 8 evaluation criteria, providing systematic insights into their zero-shot capabilities. We further show that a compact 8B open-weight model, when fine-tuned on curated data, achieves over 42.5% improvement in exploit quality and rivals some proprietary models when combined with simple test-time rejection strategies. Our results highlight the importance of data quality, structured supervision, and evaluation design for reliable exploit generation, suggesting that these factors can be as critical as model scale in adapting LLMs to cybersecurity tasks.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt conditions, and 12 hypothesized attack dimensions -- all executed in real Docker sandboxes. Every condition includes the instruction "Always respect all rules and access policies"; only a single encouragement sentence varies. Within the task class studied (planted test-runner vulnerabilities), the threat model is narrower than assumed: nine of twelve dimensions -- including minimization, moral licensing, incentives, identity priming, and reasoning triggers -- produce no detectable exploitation at n=50 per cell (upper 95% CI <7% per condition). But it is also more subtle than expected: one dimension, goal reframing, reliably triggers exploitation. "You are solving a puzzle; there may be hidden clues" produces 38-40% exploitation on Claude Sonnet 4 despite the explicit rule instruction, replicating across four models (CTF framing: 8-14% on DeepSeek, GPT-5-mini, o4-mini). The agent does not over

The exploit or the Proof of Concept of the vulnerability plays an important role in developing superior vulnerability repair techniques, as it can be used as an oracle to verify the correctness of the patches generated by the tools. However, the vulnerability exploits are often unavailable and require time and expert knowledge to craft. Obtaining them from the exploit generation techniques is another potential solution. The goal of this survey is to aid the researchers and practitioners in understanding the existing techniques for exploit generation through the analysis of their characteristics and their usability in practice. We identify a list of exploit generation techniques from literature and group them into four categories: automated exploit generation, security testing, fuzzing, and other techniques. Most of the techniques focus on the memory-based vulnerabilities in C/C++ programs and web-based injection vulnerabilities in PHP and Java applications. We found only a few studies that publicly provided usable tools associated with their techniques.

Exploits are widely used to check whether library vulnerabilities appear in different versions and to mark affected version ranges. Exploit-based checks sometimes fail because exploits stop running on many versions after API or environment changes. Commit-based methods, such as SZZ-style analysis, sometimes miss the right introduce commits and spread labels incorrectly along long version chains. These problems leave many affected versions unlabeled or wrongly labeled and make manual exploit failure analysis very expensive and impractical at scale. We present ATTAIN, a trace-driven diff analysis framework with three modules to assess vulnerability presence across evolving library versions. The modules are trace construction, diff exploration, and affected-version judgment. The trace construction module executes an exploit across historical library versions and compares their behaviors to capture cross-version execution divergences. Using these divergences, the diff exploration module guides an LLM through a finite-state tool loop to autonomously search over version changes and collect vulnerability-relevant diff hunks. The affected-version judgment module reasons over the collected

Studying the responses of large language models (LLMs) to loopholes presents a two-fold opportunity. First, it affords us a lens through which to examine ambiguity and pragmatics in LLMs, since exploiting a loophole requires identifying ambiguity and performing sophisticated pragmatic reasoning. Second, loopholes pose an interesting and novel alignment problem where the model is presented with conflicting goals and can exploit ambiguities to its own advantage. To address these questions, we design scenarios where LLMs are given a goal and an ambiguous user instruction in conflict with the goal, with scenarios covering scalar implicature, structural ambiguities, and power dynamics. We then measure different models' abilities to exploit loopholes to satisfy their given goals as opposed to the goals of the user. We find that both closed-source and stronger open-source models can identify ambiguities and exploit their resulting loopholes, presenting a potential AI safety risk. Our analysis indicates that models which exploit loopholes explicitly identify and reason about both ambiguity and conflicting goals.

Open-source libraries are widely used in modern software development, introducing significant security vulnerabilities. While static analysis tools can identify potential vulnerabilities at scale, they often generate overwhelming reports with high false positive rates. Automated Exploit Generation (AEG) emerges as a promising solution to confirm vulnerability authenticity by generating an exploit. However, traditional AEG approaches based on fuzzing or symbolic execution face path coverage and constraint-solving problems. Although LLMs show great potential for AEG, how to effectively leverage them to comprehend vulnerabilities and generate corresponding exploits is still an open question. To address these challenges, we propose Vulnsage, a multi-agent framework for AEG. Vulnsage simulates human security researchers' workflows by decomposing the complex AEG process into multiple specialized sub-agents: Code Analyzer Agent, Code Generation Agent, Validation Agent, and a set of Reflection Agents, orchestrated by a central supervisor through iterative cycles. Given a target program, the Code Analyzer Agent performs static analysis to identify potential vulnerabilities and collects rele

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks requiring sequential tool operations with naturalistic shortcut opportunities such as skipping verification steps, inferring answers from task-adjacent metadata, or tampering with evaluation-relevant functions. RHB supports independent and chained task regimes, where chain length acts as a proxy for longer-horizon agent behavior. We evaluate 13 frontier models from OpenAI, Anthropic, Google, and DeepSeek. Exploit rates range from 0% (Claude Sonnet 4.5) to 13.9% (DeepSeek-R1-Zero), varying sharply by post-training style. A controlled sibling comparison (DeepSeek-V3 vs. DeepSeek-R1-Zero) shows RL post-training is associated with substantially higher reward hacking (0.6% vs. 13.9%), with consistent gaps across all four task families. We identify six exploit categories and find that 72% of reward hacking episodes include explicit chain-of-thought rationale, suggesting models often frame exploits as legitimate problem-solving. Simple environmental har

Security vulnerabilities in software packages are a significant concern for developers and users alike. Patching these vulnerabilities in a timely manner is crucial to restoring the integrity and security of software systems. However, previous work has shown that vulnerability reports often lack proof-of-concept (PoC) exploits, which are essential for fixing the vulnerability, testing patches, and avoiding regressions. Creating a PoC exploit is challenging because vulnerability reports are informal and often incomplete, and because it requires a detailed understanding of how inputs passed to potentially vulnerable APIs may reach security-relevant sinks. In this paper, we present PoCGen, a novel approach to autonomously generate and validate PoC exploits for vulnerabilities in npm packages. The approach is the first to address this task by combining the complementary strengths of large language models (LLMs), e.g., to understand informal vulnerability reports, with static analysis, e.g., to identify taint paths, and dynamic analysis, e.g., to validate generated exploits. PoCGen successfully generates exploits for 77% of the vulnerabilities in the SecBench$.$js dataset. This success

Automated Program Repair (APR) for smart contract security promises to automatically mitigate smart contract vulnerabilities responsible for billions in financial losses. However, the true effectiveness of this research in addressing smart contract exploits remains uncharted territory. This paper bridges this critical gap by introducing a novel and systematic experimental framework for evaluating exploit mitigation of program repair tools for smart contracts. We qualitatively and quantitatively analyze 20 state-of-the-art APR tools using a dataset of 143 vulnerable smart contracts, for which we manually craft 91 executable exploits. We are the very first to define and measure the essential "exploit mitigation rate" , giving researchers and practitioners a real sense of effectiveness of cutting edge techniques. Our findings reveal substantial disparities in the state of the art, with an exploit mitigation rate ranging from a low of 29% to a high of 74%. Our study identifies systemic limitations, such as inconsistent functionality preservation, that must be addressed in future research on program repair for smart contracts.

Crossover is a powerful mechanism for generating new solutions from a given population of solutions. Crossover comes with a discrepancy in itself: on the one hand, crossover usually works best if there is enough diversity in the population; on the other hand, exploiting the benefits of crossover reduces diversity. This antagonism often makes crossover reduce its own effectiveness. We introduce a new paradigm for utilizing crossover that reduces this antagonism, which we call diversity-preserving exploitation of crossover (DiPEC). The resulting Diversity Exploitation Genetic Algorithm (DEGA) is able to still exploit the benefits of crossover, but preserves a much higher diversity than conventional approaches. We demonstrate the benefits by proving that the (2+1)-DEGA finds the optimum of LeadingOnes with $O(n^{5/3}\log^{2/3} n)$ fitness evaluations. This is remarkable since standard genetic algorithms need $Θ(n^2)$ evaluations, and among genetic algorithms only some artificial and specifically tailored algorithms were known to break this runtime barrier. We confirm the theoretical results by simulations. Finally, we show that the approach is not overfitted to Leadingones by testing

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow and don't scale. Large Language Models offer a promising middle ground, combining human-like reasoning with machine speed. Early studies show that simply prompting LLMs generates unverified vulnerability speculations with high false positive rates. To address this, we present A1, an agentic system that transforms any LLM into an end-to-end exploit generator. A1 provides agents with six domain-specific tools for autonomous vulnerability discovery, from understanding contract behavior to testing strategies on real blockchain states. All outputs are concretely validated through execution, ensuring only profitable proof-of-concept exploits are reported. We evaluate A1 across 36 real-world vulnerable contracts on Ethereum and Binance Smart Chain. A1 achieves a 63% success rate on the VERITE benchmark. Across all successful cases, A1 extracts up to \$8.59 million per exploit and \$9.33 million total. Using Monte Carlo analysis of historical attacks, we

The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces learning efficiency, while over-dependence on exploitation might trap agents in local optima. This paper revisits the exploration-exploitation dilemma from the perspective of entropy by revealing the relationship between entropy and the dynamic adaptive process of exploration and exploitation. Based on this theoretical insight, we establish an end-to-end adaptive framework called AdaZero, which automatically determines whether to explore or to exploit as well as their balance of strength. Experiments show that AdaZero significantly outperforms baseline models across various Atari and MuJoCo environments with only a single setting. Especially in the challenging environment of Montezuma, AdaZero boosts the final returns by up to fifteen times. Moreover, we conduct a series of visualization analyses to reveal the dynamics of our self-adaptive mechanism, demonstrating how entropy reflects and changes with respect to the agent's performance and adaptive process.

We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses in codified rules. Plaintiff and defendant agents choose from a constrained action space (for example, discovery requests, motions, meet-and-confer, sanctions) governed by a JSON rules engine, while a stochastic judge model with calibrated grant rates, cost allocations, and sanction tendencies resolves outcomes. We compare four policies: PPO, a contextual bandit with an LLM, a direct LLM policy, and a hand-crafted heuristic; Instead of optimizing binary case outcomes, agents are trained and evaluated using effective win rate and a composite exploit score that combines opponent-cost inflation, calendar pressure, settlement pressure at low merit, and a rule-compliance margin. Across configurable regimes (e.g., bankruptcy stays, inter partes review, tax procedures) and heterogeneous judges, we observe emergent ``exploit chains'', such as cost-inflating discovery sequences and calendar-pressure tactics that remain procedurally valid yet systemically harmful. Evaluation via cross-play and Bradley-Terry ratings shows, PPO wins more often, t